Journal articles on the topic 'Speech forensics'
To see the other types of publications on this topic, follow the link: Speech forensics.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Speech forensics.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Lei, Lei, and She Kun. "Speaker Recognition Using Wavelet Cepstral Coefficient, I-Vector, and Cosine Distance Scoring and Its Application for Forensics." Journal of Electrical and Computer Engineering 2016 (2016): 1–11. http://dx.doi.org/10.1155/2016/4908412.
Full textAbstract:
An important application of speaker recognition is forensics. However, the accuracy of speaker recognition in forensic cases often drops off rapidly because of the ill effect of ambient noise, variable channel, different duration of speech data, and so on. Therefore, finding a robust speaker recognition model is very important for forensics. This paper builds a new speaker recognition model based on wavelet cepstral coefficient (WCC), i-vector, and cosine distance scoring (CDS). This model firstly uses the WCC to transform the speech into spectral feature vecors and then uses those spectral feature vectors to train the i-vectors that represent the speeches having different durations. CDS is used to compare the i-vectors to give out the evidence. Moreover, linear discriminant analysis (LDA) and the within-class covariance normalization (WCNN) are added to the CDS algorithm to deal with the channel variability problem. Finally, the likelihood ratio estimates the strength of the evidence. We use the TIMIT database to evaluate the performance of the proposed model. The experimental results show that the proposed model can effectively solve the troubles of forensic scenario, but the time cost of the method is high.
2
Garcia‐Romero, Daniel, and Carol Espy‐Wilson. "Speech forensics: Automatic acquisition device identification." Journal of the Acoustical Society of America 127, no. 3 (March 2010): 2044. http://dx.doi.org/10.1121/1.3385386.
Full text
3
Muhammad, Ghulam, and Khalid Alghathbar. "Environment Recognition for Digital Audio Forensics Using MPEG-7 and MEL Cepstral Features." Journal of Electrical Engineering 62, no. 4 (July 1, 2011): 199–205. http://dx.doi.org/10.2478/v10187-011-0032-0.
Full textAbstract:
Environment Recognition for Digital Audio Forensics Using MPEG-7 and MEL Cepstral FeaturesEnvironment recognition from digital audio for forensics application is a growing area of interest. However, compared to other branches of audio forensics, it is a less researched one. Especially less attention has been given to detect environment from files where foreground speech is present, which is a forensics scenario. In this paper, we perform several experiments focusing on the problems of environment recognition from audio particularly for forensics application. Experimental results show that the task is easier when audio files contain only environmental sound than when they contain both foreground speech and background environment. We propose a full set of MPEG-7 audio features combined with mel frequency cepstral coefficients (MFCCs) to improve the accuracy. In the experiments, the proposed approach significantly increases the recognition accuracy of environment sound even in the presence of high amount of foreground human speech.
4
Renza, Diego, Jaisson Vargas, and Dora M. Ballesteros. "Robust Speech Hashing for Digital Audio Forensics." Applied Sciences 10, no. 1 (December 28, 2019): 249. http://dx.doi.org/10.3390/app10010249.
Full textAbstract:
The verification of the integrity and authenticity of multimedia content is an essential task in the forensic field, in order to make digital evidence admissible. The main objective is to establish whether the multimedia content has been manipulated with significant changes to its content, such as the removal of noise (e.g., a gunshot) that could clarify the facts of a crime. In this project we propose a method to generate a summary value for audio recordings, known as hash. Our method is robust, which means that if the audio has been modified slightly (without changing its significant content) with perceptual manipulations such as MPEG-4 AAC, the hash value of the new audio is very similar to that of the original audio; on the contrary, if the audio is altered and its content changes, for example with a low pass filter, the new hash value moves away from the original value. The method starts with the application of MFCC (Mel-frequency cepstrum coefficients) and the reduction of dimensions through the analysis of main components (principal component analysis, PCA). The reduced data is encrypted using as inputs two values from a particular binarization system using Collatz conjecture as the basis. Finally, a robust 96-bit code is obtained, which varies little when perceptual modifications are made to the signal such as compression or amplitude modification. According to experimental tests, the BER (bit error rate) between the hash value of the original audio recording and the manipulated audio recording is low for perceptual manipulations, i.e., 0% for FLAC and re-quantization, 1% in average for volume (−6 dB gain), less than 5% in average for MPEG-4 and resampling (using the FIR anti-aliasing filter); but more than 25% for non-perceptual manipulations such as low pass filtering (3 kHz, fifth order), additive noise, cutting and copy-move.
5
Wafula, George, and Andrew M. "Social Media Forensics for Hate Speech Opinion Mining." International Journal of Computer Applications 155, no. 1 (December 15, 2016): 39–47. http://dx.doi.org/10.5120/ijca2016912258.
Full text
6
Zhang, Yujin, Shuxian Dai, Wanqing Song, Lijun Zhang, and Dongmei Li. "Exposing Speech Resampling Manipulation by Local Texture Analysis on Spectrogram Images." Electronics 9, no. 1 (December 25, 2019): 23. http://dx.doi.org/10.3390/electronics9010023.
Full textAbstract:
Speech tampering may be aided by the resampling operation. It is significant for speech forensics to effectively detect the resampling; however, there are few studies on speech resampling detection. The purpose of this paper was therefore to provide a new training ideal to detect speech resampling. After resampling, the speech signal changes regularly in the time–frequency domain. In this paper, we theoretically analyzed the corresponding relationship between time domain and frequency domain of the resampled speech. Compared with the original speech, the bandwidth of resampled speech was stretched or compressed. First, the spectrogram was generated by short-time Fourier transform (STFT) from the speech. Then, the local binary pattern (LBP) operator was applied to model the statistical changes in the spectrogram and the LBP histogram was calculated as discriminative features. Finally, a support vector machine (SVM) was applied to classify the developed features to identify whether the speech had undergone the resampling operation. The experimental results show that the proposed method has superior detection performance in different resampling scenarios than some existing methods, and the proposed features are very robust against the commonly used compression post-processing operation. This highlights the promising potential of the proposed method as a speech resampling detection tool in practical forensics applications.
7
Liu, Zhenghui, Jiwu Huang, Xingming Sun, and Chuanda Qi. "A security watermark scheme used for digital speech forensics." Multimedia Tools and Applications 76, no. 7 (April 21, 2016): 9297–317. http://dx.doi.org/10.1007/s11042-016-3533-9.
Full text
8
Jiang, Yi, and Dengpan Ye. "Black-Box Adversarial Attacks against Audio Forensics Models." Security and Communication Networks 2022 (January 17, 2022): 1–8. http://dx.doi.org/10.1155/2022/6410478.
Full textAbstract:
Speech synthesis technology has made great progress in recent years and is widely used in the Internet of things, but it also brings the risk of being abused by criminals. Therefore, a series of researches on audio forensics models have arisen to reduce or eliminate these negative effects. In this paper, we propose a black-box adversarial attack method that only relies on output scores of audio forensics models. To improve the transferability of adversarial attacks, we utilize the ensemble-model method. A defense method is also designed against our proposed attack method under the view of the huge threat of adversarial examples to audio forensics models. Our experimental results on 4 forensics models trained on the LA part of the ASVspoof 2019 dataset show that our attacks can get a 99 % attack success rate on score-only black-box models, which is competitive to the best of white-box attacks, and 60 % attack success rate on decision-only black-box models. Finally, our defense method reduces the attack success rate to 16 % and guarantees 98 % detection accuracy of forensics models.
9
Zuhriyanto, Ikhsan, Anton Yudhana, and Imam Riadi. "Comparative analysis of Forensic Tools on Twitter applications using the DFRWS method." Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 4, no. 5 (October 30, 2020): 829–36. http://dx.doi.org/10.29207/resti.v4i5.2152.
Full textAbstract:
Current crime is increasing, one of which is the crime of using social media, although no crime does not leave digital evidence. Twitter application is a social media that is widely used by its users. Acts of crime such as fraud, insults, hate speech, and other crimes lately use many social media applications, especially Twitter. This research was conducted to find forensic evidence on the social media Twitter application that is accessed using a smartphone application using the Digital Forensics Research Workshop (DFRWS) method. These digital forensic stages include identification, preservation, collection, examination, analysis, and presentation in finding digital evidence of crime using the MOBILedit Forensic Express software and Belkasoft Evidence Center. Digital evidence sought on smartphones can be found using case scenarios and 16 variables that have been created so that digital proof in the form of smartphone specifications, Twitter accounts, application versions, conversations in the way of messages and status. This study's results indicate that MOBILedit Forensic Express digital forensic software is better with an accuracy rate of 85.75% while Belkasoft Evidence Center is 43.75%.
10
Rokanatnam, Thurgeaswary, and Hazinah Kutty Mammi. "Study on Gender Identification Based on Audio Recordings Using Gaussian Mixture Model and Mel Frequency Cepstrum Coefficient Technique." International Journal of Innovative Computing 11, no. 2 (October 31, 2021): 35–41. http://dx.doi.org/10.11113/ijic.v11n2.343.
Full textAbstract:
Speaker recognition is an ability to identify speaker’s characteristics based from spoken language. The purpose of this study is to identify gender of speakers based on audio recordings. The objective of this study is to evaluate the accuracy rate of this technique to differentiate the gender and also to determine the performance rate to classify even when using self-acquired recordings. Audio forensics uses voice recordings as part of evidence to solve cases. This study is mainly conducted to provide an easier technique to identify the unknown speaker characteristics in forensic field. This experiment is fulfilled by training the pattern classifier using gender dependent data. In order to train the model, a speech database is obtained from an online speech corpus comprising of both male and female speakers. During the testing phase, apart from the data from speech corpus, audio recordings of UTM students will too be used to determine the accuracy rate of this speaker identification experiment. As for the technique to run this experiment, Mel Frequency Cepstrum Coefficient (MFCC) algorithm is used to extract the features from speech data while Gaussian Mixture Model (GMM) is used to model the gender identifier. Noise removal was not used for any speech data in this experiment. Python software is used to extract using MFCC coefficients and model the behavior using GMM technique. Experiment results show that GMM-MFCC technique can identify gender regardless of language but with varying accuracy rate.
11
Apter, Emily. "Shibboleth: Policing by Ear and Forensic Listening in Projects by Lawrence Abu Hamdan." October 156 (May 2016): 100–115. http://dx.doi.org/10.1162/octo_a_00253.
Full textAbstract:
Drawing on the work of Lawrence Abu Hamdan, a British-Lebanese artist and researcher currently based in Beirut, this essay examines the juridical and conceptual field of critical forensis which is situated at the juncture of security studies, art, and architecture. Abu Hamdan extends forensics to the area of “new audibilities,” with a focus on the politics of juridical hearing in situations of legal-identity profiling and voice authentication (the “shibboleth test”). Abu Hamdan's projects investigate how accent monitoring and audio surveillance, voice recognition, translation technologies, sovereign acts of listening, and court determinations of linguistic norms emerge as so many technical constraints on “freedom of speech,” itself a malleable term ascribed to discrepant claims and principles, yet taking on performative force in site-specific situations.
12
Eskidere, Ömer. "Source Digital Voice Recorder Identification by Wavelet Analysis." International Journal on Artificial Intelligence Tools 25, no. 03 (June 2016): 1650016. http://dx.doi.org/10.1142/s0218213016500160.
Full textAbstract:
Identification of the speech signal origin is an important issue since it may play a vital role for criminal and forensic investigations. Yet, in the media forensics field, source digital voice recorder (DVR) identification has not been given much attention. In this paper we study the effect of subband based features obtained using uniform wavelet packet decomposition and Teager energy operator on the DVR model and brand identification performance. In order to assess the effects of these features on the proposed system, one-class classifiers (OCCs) with two reference multi-class classifiers were carried out. The performance of the DVR identification system is tested on a custom database of twelve portable DVRs of six different brands. The results showed that the proposed system can effectively identify the correct DVR brands/models with a high accuracy. Moreover, it was observed that the combination of the traditional speech features with subband Teager energy cepstral parameters (STEC) and short time frame energy as a feature improved recognition accuracy under both silent and noisy recording conditions.
13
Singh, Satyanand. "The role of speech technology in biometrics, forensics and man-machine interface." International Journal of Electrical and Computer Engineering (IJECE) 9, no. 1 (February 1, 2019): 281. http://dx.doi.org/10.11591/ijece.v9i1.pp281-288.
Full textAbstract:
<span lang="EN-US">Day by day Optimism is growing that in the near future our society will witness the Man-Machine Interface (MMI) using voice technology. Computer manufacturers are building voice recognition sub-systems in their new product lines. Although, speech technology based MMI technique is widely used before, needs to gather and apply the deep knowledge of spoken language and performance during the electronic machine-based interaction. Biometric recognition refers to a system that is able to identify individuals based on their own behavior and biological characteristics. Fingerprint success in forensic science and law enforcement applications with growing concerns relating to border control, banking access fraud, machine access control and IT security, there has been great interest in the use of fingerprints and other biological symptoms for the automatic recognition. It is not surprising to see that the application of biometric systems is playing an important role in all areas of our society. Biometric applications include access to smartphone security, mobile payment, the international border, national citizen register and reserve facilities. The use of MMI by speech technology, which includes automated speech/speaker recognition and natural language processing, has the significant impact on all existing businesses based on personal computer applications. With the help of powerful and affordable microprocessors and artificial intelligence algorithms, the human being can talk to the machine to drive and control all computer-based applications. Today's applications show a small preview of a rich future for MMI based on voice technology, which will ultimately replace the keyboard and mouse with the microphone for easy access and make the machine more intelligent.</span>
14
Palkin, Alexei D. "Alexander Shakhnarovich: A Genuine Scholar and a Wonderful Person." NSU Vestnik. Series: Linguistics and Intercultural Communication 19, no. 1 (2021): 5–14. http://dx.doi.org/10.25205/1818-7935-2021-19-1-5-14.
Full textAbstract:
This article dwells on a number of episodes related to the last years of Alexander Shakhnarovich, an outstanding Russian psycholinguist and a talented academic advisor. Alexander Shakhnarovich is known primarily for his research in child speech. The periodisation of speech development in early childhood he worked out is of particular interest. The article pinpoints that Shakhnarovich’s research was not related solely to speech development in ontogenesis, but elucidated a broader range of issues from those of general theory, like the structure of language consciousness, to those of special purposes, like linguistic expertise in forensics, dialectology, intonation and modality, peculiarities of text analysis, etc. It was Shakhnarovich’s great experience in analysing child speech that helped him to explore other psycholinguistic trends. The scientist proved to be an expert both in psycholinguistic issues that were intertwined with pure linguistics and in the psychology of speech. Alexander Shakhnarovich was a remarkable proponent of Lev Vygotsky’s scientific school whose theoretical insights made in the first half of the 20th century underlay Shakhnarovich’s findings. It is noteworthy that both Shakhnarovich and Vygotsky probed into child speech attempting to make conclusions on language capacity development as a whole and to tap into the fundamental through the applied.
15
Sidiq, Muhammad Fajar, and Muhammad Nur Faiz. "Review Tools Web Browser Forensics untuk Mendukung Pencarian Bukti Digital." Jurnal Edukasi dan Penelitian Informatika (JEPIN) 5, no. 1 (April 23, 2019): 67. http://dx.doi.org/10.26418/jp.v5i1.31430.
Full textAbstract:
Perkembangan penggunaan internet yang semakin banyak setiap tahunnya mengakibatkan penggunaan web browser juga meningkat. Hal ini berdampak pada kejahatan dengan menggunakan web browser juga meningkat seperti penyalahgunaan email, hoax, hate speech, penipuan dan lainnya. Penelitian ini menunjukkan pentingnya mengenali aktivitas penggunaan web browser dari sisi korban dan pelaku. Penggunaan web browser ini akan menentukan pola atau alur kejahatan pada suatu insiden kejahatan. Hal ini akan membantu penyidik dalam menganalisis bukti digital secara cepat dan dapat mengungkap jenis kejahatan yang terjadi secara baik. Bukti digital yang dianalisis seperti akun, kata kunci pencarian, kunjungan web, dan lainnya. Penelitian ini memberikan penjelasan lokasi penyimpanan bukti digital, format waktu yang digunakan dan 10 tools yang digunakan penyidik dalam mengungkap kejahatan dengan media web browser seperti Google Chrome, Mozilla Firefox, Internet Explorer, Safari dan Opera.
16
Khadar Nawas, K., Manish Kumar Barik, and A. Nayeemulla Khan. "Speaker Recognition using Random Forest." ITM Web of Conferences 37 (2021): 01022. http://dx.doi.org/10.1051/itmconf/20213701022.
Full textAbstract:
Speaker identification has become a mainstream technology in the field of machine learning that involves determining the identity of a speaker from his/her speech sample. A person’s speech note contains many features that can be used to discriminate his/her identity. A model that can identify a speaker has wide applications such as biometric authentication, security, forensics and human-machine interaction. This paper implements a speaker identification system based on Random Forest as a classifier to identify the various speakers using MFCC and RPS as feature extraction techniques. The output obtained from the Random Forest classifier shows promising result. It is observed that the accuracy level is significantly higher in MFCC as compared to the RPS technique on the data taken from the well-known TIMIT corpus dataset.
17
BAKIR, Çiğdem. "Compressing English Speech Data with Hybrid Methods without Data Loss." International Journal of Applied Mathematics Electronics and Computers 10, no. 3 (September 30, 2022): 68–75. http://dx.doi.org/10.18100/ijamec.1166951.
Full textAbstract:
Understanding the mechanism of speech formation is of great importance in the successful coding of the speech signal. It is also used for various applications, from authenticating audio files to connecting speech recording to data acquisition device (e.g. microphone). Speech coding is of vital importance in the acquisition, analysis and evaluation of sound, and in the investigation of criminal events in forensics. For the collection, processing, analysis, extraction and evaluation of speech or sounds recorded as audio files, which play an important role in crime detection, it is necessary to compress the audio without data loss. Since there are many voice changing software available today, the number of recorded speech files and their correct interpretation play an important role in detecting originality. Using various techniques such as signal processing, noise extraction, filtering on an incomprehensible speech recording, improving the speech, making them comprehensible, determining whether there is any manipulation on the speech recording, understanding whether it is original, whether various methods of addition and subtraction are used, coding of sounds, the code must be decoded and the decoded sounds must be transcribed. In this study, first of all, what sound coding is, its purposes, areas of use, classification of sound coding according to some features and techniques are given. Moreover, in our study speech coding was done on the English audio data. This dataset is the real dataset and consists of approximately 100000 voice recordings. Speech coding was done using waveform, vocoders and hybrid methods and the success of all the methods used on the system we created was measured. Hybrid models gave more successful results than others. The results obtained will set an example for our future work.
18
Amjad, Ammar, Lal Khan, and Hsien-Tsung Chang. "Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition." PeerJ Computer Science 8 (August 3, 2022): e1053. http://dx.doi.org/10.7717/peerj-cs.1053.
Full textAbstract:
Speech emotion recognition (SER) systems have evolved into an important method for recognizing a person in several applications, including e-commerce, everyday interactions, law enforcement, and forensics. The SER system’s efficiency depends on the length of the audio samples used for testing and training. However, the different suggested models successfully obtained relatively high accuracy in this study. Moreover, the degree of SER efficiency is not yet optimum due to the limited database, resulting in overfitting and skewing samples. Therefore, the proposed approach presents a data augmentation method that shifts the pitch, uses multiple window sizes, stretches the time, and adds white noise to the original audio. In addition, a deep model is further evaluated to generate a new paradigm for SER. The data augmentation approach increased the limited amount of data from the Pakistani racial speaker speech dataset in the proposed system. The seven-layer framework was employed to provide the most optimal performance in terms of accuracy compared to other multilayer approaches. The seven-layer method is used in existing works to achieve a very high level of accuracy. The suggested system achieved 97.32% accuracy with a 0.032% loss in the 75%:25% splitting ratio. In addition, more than 500 augmentation data samples were added. Therefore, the proposed approach results show that deep neural networks with data augmentation can enhance the SER performance on the Pakistani racial speech dataset.
19
Qin, Tianyun, Rangding Wang, Diqun Yan, and Lang Lin. "Source Cell-Phone Identification in the Presence of Additive Noise from CQT Domain." Information 9, no. 8 (August 17, 2018): 205. http://dx.doi.org/10.3390/info9080205.
Full textAbstract:
With the widespread availability of cell-phone recording devices, source cell-phone identification has become a hot topic in multimedia forensics. At present, the research on the source cell-phone identification in clean conditions has achieved good results, but that in noisy environments is not ideal. This paper proposes a novel source cell-phone identification system suitable for both clean and noisy environments using spectral distribution features of constant Q transform (CQT) domain and multi-scene training method. Based on the analysis, it is found that the identification difficulty lies in different models of cell-phones of the same brand, and their tiny differences are mainly in the middle and low frequency bands. Therefore, this paper extracts spectral distribution features from the CQT domain, which has a higher frequency resolution in the mid-low frequency. To evaluate the effectiveness of the proposed feature, four classification techniques of Support Vector Machine (SVM), Random Forest (RF), Convolutional Neural Network (CNN) and Recurrent Neuron Network-Long Short-Term Memory Neural Network (RNN-BLSTM) are used to identify the source recording device. Experimental results show that the features proposed in this paper have superior performance. Compared with Mel frequency cepstral coefficient (MFCC) and linear frequency cepstral coefficient (LFCC), it enhances the accuracy of cell-phones within the same brand, whether the speech to be tested comprises clean speech files or noisy speech files. In addition, the CNN classification effect is outstanding. In terms of models, the model is established by the multi-scene training method, which improves the distinguishing ability of the model in the noisy environment than single-scenario training method. The average accuracy rate in CNN for clean speech files on the CKC speech database (CKC-SD) and TIMIT Recaptured Database (TIMIT-RD) databases increased from 95.47% and 97.89% to 97.08% and 99.29%, respectively. For noisy speech files with seen noisy types and unseen noisy types, the performance was greatly improved, and most of the recognition rates exceeded 90%. Therefore, the source identification system in this paper is robust to noise.
20
Farid, Mifta Nur, Dani Dwi Putra, and Barokatun Hasanah. "Pengaruh Perubahan Pitch dan Formant Terhadap Hasil Identifikasi Kepemilikan Suara Dengan Metode Audio Forensik." JTT (Jurnal Teknologi Terpadu) 9, no. 1 (May 4, 2021): 1–8. http://dx.doi.org/10.32487/jtt.v9i1.894.
Full textAbstract:
Audio forensics is a field of science that analyzes audio such as sound recordings. Voice recordings always have information in the form of frequency characteristics, the identities of these frequencies can be identified. Furthermore, an analysis of changes in pitch and formant will be carried out. This study used pitch analysis and analysis of variance on formants. With the correct procedure for handling recorded sound evidence which is then followed by procedural examination and analysis, it is hoped that the results of the voice recognition examination can scientifically show the ownership of the voice in the recording. Based on the results of the overall analysis of the sound recordings of evidence and comparison after carrying out various stages of analysis, the voice recordings are "not identical" from the same person. The thing that causes the inequality in voice identification is the difference in intonation or tone of the subject's speech when the voice is recorded.
21
Al-Karawi, Khamis A. "Robustness Speaker Recognition Based on Feature Space in Clean and Noisy Condition." International Journal of Sensors, Wireless Communications and Control 9, no. 4 (September 17, 2019): 497–506. http://dx.doi.org/10.2174/2210327909666181219143918.
Full textAbstract:
Background & Objective: Speaker Recognition (SR) techniques have been developed into a relatively mature status over the past few decades through development work. Existing methods typically use robust features extracted from clean speech signals, and therefore in idealized conditions can achieve very high recognition accuracy. For critical applications, such as security and forensics, robustness and reliability of the system are crucial. Methods: The background noise and reverberation as often occur in many real-world applications are known to compromise recognition performance. To improve the performance of speaker verification systems, an effective and robust technique is proposed to extract features for speech processing, capable of operating in the clean and noisy condition. Mel Frequency Cepstrum Coefficients (MFCCs) and Gammatone Frequency Cepstral Coefficients (GFCC) are the mature techniques and the most common features, which are used for speaker recognition. MFCCs are calculated from the log energies in frequency bands distributed over a mel scale. While GFCC has been acquired from a bank of Gammatone filters, which was originally suggested to model human cochlear filtering. This paper investigates the performance of GFCC and the conventional MFCC feature in clean and noisy conditions. The effects of the Signal-to-Noise Ratio (SNR) and language mismatch on the system performance have been taken into account in this work. Conclusion: Experimental results have shown significant improvement in system performance in terms of reduced equal error rate and detection error trade-off. Performance in terms of recognition rates under various types of noise, various Signal-to-Noise Ratios (SNRs) was quantified via simulation. Results of the study are also presented and discussed.
22
Kohsasih, Kelvin Leonardi, and B. Herawan Hayadi. "Classification SARS-CoV-2 Disease based on CT-Scan Image Using Convolutional Neural Network." Scientific Journal of Informatics 9, no. 2 (November 30, 2022): 197–204. http://dx.doi.org/10.15294/sji.v9i2.36583.
Full textAbstract:
Purpose: Convolutional Neural Network (CNN) is one of the most popular and widely used deep learning algorithms. These algorithms are commonly used in various applications, including image processing in medical and digital forensics, speech recognition, and other academic disciplines. SARS-CoV-2 (COVID-19) is a disease that first appeared in Wuhan, China, and has symptoms similar to pneumonia. This study aims to classify the covid-19 virus by proposing a deep learning model to prevent infection rates.Methods: The dataset used in this study is a public dataset originating from a hospital in Sao Paulo, Brazil. The data images consisted of 1252 infected with covid and 1230 data classified as non-covid but have other lung diseases. The classification method proposed in this research is a CNN model based on Resnet 50.Result: The experimental results show that the proposed Resnet 50-based convolutional neural network model works well in classifying SARS-CoV-2 disease using CT-Scan images. Our proposed model obtains 95% accuracy, precision, recall, and f1 values on the Epoch 500.Novelty: In this experiment, we utilized the Resnet50-based CNN model to classify the SARS-CoV-2 (COVID-19) disease using CT-Scan images and got good performance.
23
Zhang, Zhenyu, Xianfeng Zhao, and Xiaowei Yi. "ASLNet: An Encoder-Decoder Architecture for Audio Splicing Detection and Localization." Security and Communication Networks 2022 (March 29, 2022): 1–9. http://dx.doi.org/10.1155/2022/8241298.
Full textAbstract:
Audio splicing means inserting an audio segment into another audio, which presents a great challenge to audio forensics. In this paper, a novel audio splicing detection and localization method based on an encoder-decoder architecture (ASLNet) is proposed. Firstly, an audio clip is divided into several small audio segments according to the size of the smallest localization region L slr , and the acoustic feature matrix and corresponding binary ground truth mask are created from each audio segment. Then, we concatenate acoustic feature matrices from all segments of an audio clip into an acoustic feature matrix and send it to a fully convolutional network (FCN) based encoder-decoder architecture which consists of a series of convolutional, pooling and transposed convolutional layers to get a binary output mask. Next, the binary output mask is divided into small segments according to the L slr , and the ratio ρ of the number of elements equal to one to the number of all elements in a small segment is calculated. Finally, we compare ρ with the predetermined threshold T to determine whether the corresponding audio segment is spliced. We evaluate the effectiveness of the proposed ASLNet on four datasets produced from publicly available speech corpus. Extensive experiments show that the best detection accuracy of ASLNet for the intradatabase and cross-database evaluation can achieve 0.9965 and 0.9740 receptively, which outperforms the state-of-the-art method.
24
Kusno, Ali, M. Bahri Arifin, and Widyatmike Gede Mulawarman. "PENGUNGKAPAN MUATAN UJARAN KEBENCIAN BERDASARKAN KESUKUAN PADA BAHASA SEBAGAI ALAT BUKTI HUKUM: ANALISIS LINGUISTIK FORENSIK (DISCLOSURE OF HATE SPEAKING BASED ON ETHNICITY ON LANGUAGE AS LEGAL EVIDENCE: FORENSIC LINGUISTIC ANALYSIS)." JURNAL BAHASA, SASTRA DAN PEMBELAJARANNYA 12, no. 2 (October 11, 2022): 235. http://dx.doi.org/10.20527/jbsp.v12i2.12721.
Full textAbstract:
Disclosure of Content of Hate Speech Based on Ethnicity in Legal Evidence: Forensic Linguistic Analysis. This study aims to reveal allegations of hate speech based on SARA. This research uses descriptive qualitative research with research data in the form of the use of language as legal evidence in uploading SL (Reported) and information from police investigators. The analytical approach uses triangulation theory, namely the analysis of critical discourse models of Fairclough, sociopragmatics, and Roland Barthes' semiotics. This study concludes that SL uploads are strongly suspected of causing hatred or hostility to individuals and/or groups based on SARA between tribal organizations (KP and PB organizations). Handling such cases needs to be done quickly because they have the potential to cause communal social conflicts.Keywords: SARA hate speech, critical discourse analysis of legal cases, speech acts, semiotics, forensic linguisticsPengungkapan Muatan Ujaran Kebencian Berdasarkan Kesukuan pada Alat Bukti Hukum: Analisis Linguistik Forensik. Penelitian ini bertujuan mengungkap dugaan ujaran kebencian berdasarkan SARA. Penelitian menggunakan kualitatif deskriptif dengan data penelitian berupa penggunaan bahasa sebagai alat bukti hukum dalam unggahan SL (Terlapor) dan keterangan penyidik kepolisian. Pendekatan analisis menggunakan triangulasi teori, yakni analisis wacana kritis model Fairclough, sosiopragmatik, dan semiotik Roland Barthes. Penelitian ini menyimpulkan bahwa unggahan SL diduga kuat menimbulkan rasa kebencian atau permusuhan individu dan/atau kelompok berdasarkan SARA antarormas kesukuan (ormas KP dan PB). Penanganan kasus seperti itu perlu dilakukan dengan cepat karena berpotensi menimbulkan konflik sosial komunal.Kata-kata Kunci: ujaran kebencian SARA, analisis wacana kritis kasus hukum, tindak tutur, semiotik, linguistik forensik
25
Karenisa, Kity. "PENGHINAAN TERHADAP SIMBOL DAN PEJABAT NEGARA DALAM KAJIAN LINGUISTIK FORENSIK." TELAGA BAHASA 7, no. 1 (January 15, 2020): 55–72. http://dx.doi.org/10.36843/tb.v7i1.57.
Full textAbstract:
AbstrakTulisan ini mendeskripsikan bagaimana kajian linguistik forensik dilakukan dalam delik aduan penghinaan terhadap simbol dan pejabat negara. Data dikumpulkan dan diolah menjadi transkripsi forensik dari tuturan berupa video dan tangkap layar unggahan Facebook yang mengandung tuturan yang berkasus hukum sebagai data tersedia prakasus, serta video dan tangkap layar unggahan Facebook dengan topik serupa dari subjek penelitian yang sama sebagai data galian kasus. Tuturan yang berkasus hukum dianalisis secara semantis dan pragmatik. Analisis semantis digunakan untuk memperoleh gambaran makna sekunder tuturan yang disampaikan tersidik. Analisis pragmatik digunakan untuk memperoleh makna berdasarkan konteks tuturan tersidik. Perbandingan data tuturan berdelik hukum dengan tuturan dari data pembanding digunakan untuk memperoleh gambaran profil bahasa tersidik berdasarkan gaya diksi tersidik. Hasil analisis menunjukkan bahwa transkripsi forensik dari data tuturan seperti video atau tulisan di media sosial dijadikan dasar untuk melakukan analisis dalam kajian linguistik forensik. Berdasarkan analisis semantis dengan melihat penggunaan kata, frasa, dan kalimat juga dilihat koteks penggunaannya dan berdasarkan analisis pragmatik dengan melihat konteks penggunaannya disimpulkan bahwa HRS tidak melakukan penghinaan terhadap Pancasila, HBS melakukan penghinaan terhadap pejabat negara, dan SSG tidak melakukan penghinaan terhadap simbol atau lambang negara, yaitu Pancasila.Kata kunci: penghinaan, simbol, negara, linguistik forensikInsulting the State Symbol and Official in Forensic Linguistics Studies AbstractThis paper is describes on how the study of forensic linguistics conducted in the complaint offense of insulting against the state symbols and officials. Data is collected and processed into a forensic transcriptions from videos and screenshots uploaded on Facebook containing legal-related speeches as a pre case provided data, as well as videos and screenshots uploaded on Facebook with similar to the same research subject as a case study data. The Legal-related speeches are analyzed semantically and pragmatically. Semantic analysis is used to obtain a picture of the secondary meaning of the speeches expressed by the accused. A pragmatic analysis is used to gain meaning based on the speeches of the accused context. Comparison of the legal-related speeches data with the speeches of comparative data is used to obtain an overview of the language profile of the accused based on the diction style used by the accused. The result of the analysis indicates that the forensic transcriptions from the videos and posts on social media are used as a basis for conducting analysis in forensic linguistics studies. Based on the semantic analysis by looking at the use of words, phrases, and sentences as well as the usage co-text, and based on the pragmatic analysis by looking at the usage context, it was concluded that HRS did not insult Pancasila, HBS insulted the state officials, and SSG did not insult the state symbols, namely Pancasila.Keywords: insults, symbols, state, forensic linguistics
26
Worthington, I. "Once More, The Client/ Logographos Relationship." Classical Quarterly 43, no. 1 (May 1993): 67–72. http://dx.doi.org/10.1017/s0009838800044189.
Full textAbstract:
Whilst Theophrastus (Char. 17.8) implies that the logographos had a great deal of control over the oral version of a forensic speech and what went into it,2 the part played by the logographos and the client in the content and circulation of the oration after oral delivery is controversial, and has attracted a fair share of attention.3 Sir Kenneth Dover argued that joint or composite authorship of the speech (i.e. client and logographos together) could take place, and that it was the client who could publish the speech after the trial and was free to include his own remarks.4 Thus, as Dover would have it, in the case of Lysias (and of other orators too if joint composition occurred), no unique style of that orator could be discerned in his speeches as we have them today. This composite authorship was first questioned by T. N. Winter,5 and denied even more vigorously by S. Usher,6 who argued that responsibility for a speech's later circulation lay only with the logographos, who also revised the speech as he saw fit.7 Their arguments, which nicely complement each other, are convincing enough on the evidence we have (although a case will be made below that in certain circumstances some, but probably not many, speeches appear to be the work of joint authorship). However, two other factors may be brought in as further support: the stylistic nature of the revised speech and the extent of literacy. The argument of this paper is that the composition of the final circulated speech was beyond the ability of the ordinary client and could only have been produced by the logographos.
27
Zyubina, Irina A., Galina G. Matveeva, Marina R. Zheltukhina, Gennady G. Slyshkin, and Alevtina V. Shevchenko. "Forensic prosecutor’s speech as a speech genre." XLinguae 10, no. 3 (June 2017): 312–23. http://dx.doi.org/10.18355/xl.2017.10.03.25.
Full text
28
Hollien, Harry. "About forensic phonetics." Linguistica 52, no. 1 (December 31, 2012): 27–53. http://dx.doi.org/10.4312/linguistica.52.1.27-53.
Full textAbstract:
This article sets forth the goals and content of Forensic Phonetics and its major elements. Considered are 1) the processing and analysis of spoken utterances, 2) enhancement of speech intelligibility (re: surveillance and other recordings), 3) authentication of recordings, 4) speaker identification, and 5) detection of deception, intoxication, and emotions in speech. Stress in speech, and the psychological stress evaluation systems that some individuals attempt to use as lie detectors also will be considered.
29
Dmitrievich, Nikishin Vladimir. "Criteria of Extremist Speech Acts: Forensic Linguistic Diagnostic Complexes." European Journal of Social & Behavioural Sciences 30, no. 2 (April 29, 2021): 3394–408. http://dx.doi.org/10.15405/ejsbs.296.
Full textAbstract:
The article examines the challenges in detecting features of verbal extremism by analysing forensic practice, research papers on forensic linguistics and anti-extremist law, manuals developed by Russian law enforcement agencies and scientific and educational organizations. The article suggests a new approach to the methodological support of forensic linguistic examination of extremist discourse. This approach is based on the concept of a three-component structure of ‘extremist’ utterances. The author justifies the proposed classification of extremist speech acts and describes forensic diagnostic complexes corresponding to these speech acts. These complexes can serve as the reference samples for both linguistic experts (who conduct forensic examination) and the law enforcement officers (who conduct forensic diagnostics). The use of standardized forensic diagnostic complexes of extremist speech acts which serve as a tool for classification of illegal verbal behaviour allows to maintain the balance between the right to freedom of speech and pluralism of opinions, on the one hand, and protection against abuse of these rights (protection of media security), on the other hand.
30
Galyashina, E. I. "Speech Analysis in Legal Proceedings: Urgent Needs, Problems and Ways to Solve Them." Theory and Practice of Forensic Science 14, no. 4 (January 8, 2020): 6–18. http://dx.doi.org/10.30764/1819-2785-2019-14-4-6-18.
Full textAbstract:
The article describes the problems in legal proceedings that impede effective use of special knowledge of speech necessary to qualify offenses committed by means of speech actions. Among them the imperfection of the current legislation on forensic expert activity is mentioned, where there are no uniform professional qualifications and requirements for state forensic experts and persons who are not the employees of state forensic institutions and who are quite often involved in the conduct of linguistic expertise, authorship and phonogram examinations. It is stated that due to the lack of professional training in forensic specialties of such non-state experts, the quality of their speech analysis does not meet the need of the legal community and civil society in objective and effective examinations, the results of which could be used in trial. If the incompetence of non-state experts is revealed, their opinions are recognized as an inadmissible evidence, reexaminations are assigned to the state forensic institutions, which significantly delays the proceedings. It is proposed to legislate the mandatory certification for nonstate experts, to unify the procedure of additional professional education in the field of specific expert’s specialties for state and non-state forensic experts. In order to solve the problems mentioned above it is proposed to develop and implement a passport for each forensic specialty, a single nomenclature of forensic specialties corresponding to the types of forensic speech examinations, to unify additional professional retraining and professional development programs.
31
Sukma, Bayu Permana, Devi Ambarwati Puspitasari, Siti Afni Afiyani, Indah Okitasari, Dian Palupi, Fani Kusumawardani, Husnul Khatimah, and Reza Amarta Prayoga. "Pola tuturan perundungan siber (cyberbullying) di kalangan pelajar Indonesia." Bahasa dan Seni: Jurnal Bahasa, Sastra, Seni, dan Pengajarannya 49, no. 2 (August 31, 2021): 205. http://dx.doi.org/10.17977/um015v49i22021p205.
Full textAbstract:
Cyberbullying speech patterns among Indonesian studentsLanguage evidence is consulted in dealing with cyberbullying cases. Linguistic analysis is used to reveal the nature of speech and cyberbullying expressions that have legal implications. This study aimed to find the speech patterns used by students in cyberbullying, identify the features of insults in cyberbullying speech, and identify the legal implications of cyberbullying speech on social media. 504 speech data were collected from Facebook and Twitter from January to April 2020. They were all written in social media accounts of Indonesian high school students. The cyberbullying speech data was analyzed qualitatively using forensic linguistics analysis, i.e., analyzing the linguistic aspects of social media speech data with linguistic theory, particularly speech act theory. Results of the linguistic analysis were then linked to the legal implication of the social media speech. The analysis shows that four general patterns of cyberbullying speech are found, Head Act, Head Act - Supportive Move, Supportive Move - Head Act, and Supportive Move - Head Act - Supportive Move. In addition, three features of insults in cyberbullying are found: the use of pejorative words or phrases, the use of words or phrases with negative connotations, and the use of 'reply' or 'mention' features. The patterns of cyberbullying speech found in this study indicate that the insulting effects of different word or phrase formulation vary. However, they all may have legal implications, especially the violations of Law of Information and Electronic Transaction (UU ITE), particularly Article 27 Paragraph (3) regarding insults and defamation.Keywords: cyberbullying, social media, speech act, insults, forensic linguistics Pola tuturan perundungan siber (cyberbullying) di kalangan pelajar IndonesiaAlat bukti kebahasaan sangat diperlukan dalam penangangan kasus perundungan siber. Pembuktian tuturan perundungan siber dilakukan melalui hasil analisis linguistik yang mampu menunjukkan hakikat pertuturan dan ekspresi perundungan yang berimplikasi hukum. Tujuan penelitian ini adalah menemukan pola tuturan yang digunakan oleh pelajar dalam melakukan perundungan siber, mengidentifikasi fitur ekpresi penghinaan yang terkandung dalam tuturan perundungan siber, dan mengidentifikasi implikasi hukum tuturan pada perundungan siber di media sosial. 504 data tuturan yang berasal Instagram dan Twitter diambil pada rentang waktu Januari hingga April 2020. Seluruh data tuturan tersebut ditulis oleh akun pelajar sekolah menengah di Indonesia. Analisis data kualitatif dilakukan untuk mengkonfirmasi data tuturan perundungan siber dengan telaah linguistik forensik, yakni menganalisis aspek kebahasaan data tuturan media sosial dengan teori linguistik, khususnya teori tindak tutur. Hasil analisis linguistik kemudian dihubungkan dengan aspek implikasi hukum dari tuturan media sosial tersebut. Berdasarkan hasil analisis, ditemukan empat pola umum tuturan perundungan siber, yaitu head act, head act - supportive move, supportive move - head act, dan supportive move - head act - supportive move. Selain itu ditemukan pula tiga fitur ekspresi penghinaan dalam tuturan perundungan siber, yaitu penggunaan kata atau frasa peyoratif, penggunaan kata atau frasa berkonotasi negatif, dan penggunaan fitur membalas (reply/mention). Pola tuturan perundungan siber yang telah ditemukan dalam penelitian ini menunjukkan perbedaan efek penghinaan yang ditimbulkan dari formulasi kata atau frasa, namun semua tuturan tersebut memiliki potensi implikasi hukum, khususnya pelanggaran UU ITE, utamanya pasal 27 ayat (3) tentang penghinaan dan pencemaran nama baik.Kata kunci: perundungan siber, media sosial, tindak tutur, penghinaan, linguistik forensik
32
Nikishin, V. D. "OBJECTS OF FORENSIC LINGUISTIC EXAMINATION: NEW CHALLENGES OF CRIMINOGENIC INTERNET COMMUNICATION." Courier of Kutafin Moscow State Law University (MSAL)), no. 6 (July 31, 2020): 79–88. http://dx.doi.org/10.17803/2311-5998.2020.70.6.079-088.
Full textAbstract:
The article is devoted to the system of objects of forensic linguistic examination at the present stage of its development. The relevance of the study is tied with the activation of criminogenic Internet communication, which implements defamatory, extremist and other aggressive speech acts that create threats to the information and worldview security of Web users. The essence of the object of forensic linguistic examination is considered from the following points of view: the theory of confl ict, the criminalistic understanding of the object of forensic examination as a complex three-link dynamic system, the concept of speech traces, the language form of the speech products, the material storage mediums, etc. Defi nitions of the diagnosed and diagnosing objects of the forensic linguistic examination are proposed. The article focuses on creolized and multicode texts, their multimodal perception. The correlation of speech traces of criminogenic Internet communication and digital traces is considered.
33
Surya, Chennam Chandrika, Karunakar K, Murali Mohan T, and R. Prasanthi Kumari. "Language Variety Prediction using Word Embeddings and Machine Leaning Algorithms." International Journal for Research in Applied Science and Engineering Technology 10, no. 12 (December 31, 2022): 1616–23. http://dx.doi.org/10.22214/ijraset.2022.48280.
Full textAbstract:
Abstract: Author Profiling is a technique of predicting demographic characteristics like gender, age, location, nativity language, educational background etc., of an author by analysing their written texts. Author profiling is used in several text processing applications like forensics analysis, marketing, security. The author profiling techniques identify the stylistic differences among the author writing styles to identify the demographics of authors. Researchers experimented with various stylistic features like lexical features, content-based features, syntactic features, semantic features, domain specific features, structural features, readability features etc., to identify the stylistic differences among different author’s texts. The dataset plays an important role to analyse the stylistic differences of authors. PAN is one competition organizes different types of tasks in every year to encourage the participants around the globe for providing solutions to different types of text classification problems like plagiarism detection, authorship attribution, authorship verification, authorship profiling, celebrity profiling, style change detection, fake news spreaders detection, hate speech spreaders detection etc. The author profiling task was introduced in 2013 by the organizers of PAN competition. The organizers carefully gather the datasets and make available to the researchers for providing solutions to the problems. Every year the organizers conduct competitions on different sub-tasks of author profiling and provides datasets in different languages and in different genres. In 2017 competition, PAN introduces a task of predicting the language variety of an author. They release the dataset in four languages. In this work, we proposed an approach for English language dataset of language variety prediction. The proposed approach used the word embeddings generated by the Word2Vec model and BERT (Bidirectional Encoder Representations from Transformers) model. The word embeddings are used for generating the document vectors by combining the word embeddings of words those contain in documents. The document vectors are trained with two machine learning algorithms such as support vector machine and random forest. The Random Forest attained best accuracy of 96.87 for language variety prediction when experiment conducted with BERT embeddings
34
Mursa, Irina. "Speech Portrait of Personality as a Tool of Forensic AuthorshipAttribution." Legal Linguistics, no. 18 (29) (December 28, 2020): 16–20. http://dx.doi.org/10.14258/leglin(2020)1804.
Full textAbstract:
The article discussesapplication of speech portraitpotential in forensic authorship attribution. An illustrative example is the speech portraits of Russian vernacular native speakers of different ages and genders living in the same language community - the village of Kamyshenka, Altai Krai. The results of the study can be used for speech identification within the framework forensic authorship attribution, since the described lexical and grammatical features of the speech of each respondent form unique combinations that allow for the identification procedure. The nature of the narrative strategies in the structure of the speech portrait is also established, which are no less, if sometimes even a more informative feature of the speech portrait of a linguistic persona than the lexical and grammatical features of the speech.
35
AZHNIUK, L. V. "THREAT AS AN OBJECT OF FORENSIC LINGUISTICS." Movoznavstvo 323, no. 2 (May 10, 2022): 41–62. http://dx.doi.org/10.33190/0027-2833-323-2022-2-003.
Full textAbstract:
The article discusses methodological approaches to forensic linguistic research concerning the cases based on the juridical assessment of speech deeds. As an object of forensic linguistics the speech act lies at the interface between the conceptual spheres of linguistics and jurisprudence. When the speech deeds whose content is defined by the law (threats, blackmail, appeal, solicitation) are performed under certain communicative circumstances they could be qualified as criminal offences. Juridical assessment of such speech deeds must pursue the lines of reasoning lying beyond jurisprudence and pertaining to linguistic pragmatics. The principle of linguistic parameterization of the language crime is essential for resolution of the wide range of tasks confronting forensic linguistics investigation. Parameterization stipulates for the comprehensive list of indispensible communicative features as its linguopragmatic elements. The combination of the sum-total of linguopragmatic elements of the speech deed in the relevant communicative context is tantamount to its perpetration. Through the example of the speech act «threat» methodological approaches are described and their theoretical feasibility is discussed. The differences between the casual understanding of «threat», on the one hand, and its linguopragmatic qualification, on the other hand, are examined. Among the distinctive features of the speech act «threat» we distinguish those conditioned by the essential characteristics of the respective speech genre and those conditioned by the juridical qualification of the elements of the linguistic offence. The cases of parameterization of the linguistic crime and of the introspection of the elements of the crime in forensic linguistics are exemplified.
36
Zinsmaier, Thomas. "Zwischen Erzählung und Argumentation: colores in den pseudoquintilianischen Declamationes maiores." Rhetorica 27, no. 3 (2009): 256–73. http://dx.doi.org/10.1525/rh.2009.27.3.256.
Full textAbstract:
Abstract As a designation for specific arguments providing clever explanations or excuses in mock-forensic speeches (controversiae), the technical metaphor color is mainly known from the work of Seneca the Elder. But while the many colores he cites lack their speech context, the Major Declamations ascribed to Quintilian give a unique opportunity to study the techniques of “colouring” within the framework of entire speeches. After a reconsideration of what we know about the origin and the exact meaning of color, this article demonstrates the dual function of colores as a means both of generating arguments and of creating stories, i.e. as a device that is rhetorical as well as literary.
37
Igorevna, Galyashina Elena. "The Challenges of Forensic Linguistic Analysis of False Testimony." European Journal of Social & Behavioural Sciences 30, no. 3 (August 31, 2021): 236–50. http://dx.doi.org/10.15405/ejsbs.302.
Full textAbstract:
The present paper arises from wider research which focused on various manifestations of destructive and malicious speech behavior in spontaneous oral or written dialogs, related to the processes of information concealment and falsification in police interviews and court testimonies. A number of analytical methods were used to generate this paper: a retrospective analysis of scientific literature, comparative legal and logical analysis, extrapolation methods, and content analysis. Despite numerous experimental researches devoted to acoustic-phonetic or psycholinguistic features of lies, their results are not sufficiently reliable for forensic purposes as the expert report should not rely on assumptions. The author disputes the evidence admissibility of experts’ conclusions about utterances implying speech parameters correlating with lies detected via psycholinguistic examination in oral speech audio or video recording of a police interview or a court testimony. Forensic psycholinguistic methods and comprehensive algorithms used in some forensic experts’ reports to detect speech signs of lying demonstrate a great variety that contradicts with the principals of evidence admissibility. The insufficient development of the currently used expert approach and the lack of a unified methodology for solving expert tasks on a strictly scientific basis creates a demand for developing comprehensive methods for studying lies on the basis of forensic speech science and cognitive theory.
38
Koltunova, Elizaveta A., and Igor V. Zharkov. "The limits of application of discrediting speech strategy concept in lingvo-expert practice." Neophilology, no. 2 (2022): 218–27. http://dx.doi.org/10.20310/2587-6953-2022-8-2-218-227.
Full textAbstract:
The subject of the study is the possibility, feasibility and admissibility of the concept of discrediting speech strategy in the process of carrying out the activities of experts and specialists in the field of forensic linguistic expertise. The relevance of the analysis is due to the existence of a tendency to introduce the concepts of discrediting and the discrediting speech strategy into the norms of the current legislation and (or) the practice of forensic linguistic expertise. In the course of the study, significant features of this speech strategy were identified, and judgment about the relevance of both the concept of a discrediting speech strategy in general and its main tactics for solving a limited range of expert tasks related to identifying signs of humiliation of honor and dig-nity, defamation of business reputation of physical person and (or) legal person, insulting and slander were made and justified (only in cases, when in the disputed text negative information, ex-pressed in the form of an assertion (verifiable) in relation to these persons was identified). An ex-ample of an incorrect appeal to the conceptual framework of the discrediting speech strategy in forensic research conducted for the case of protecting the business reputation of a legal entity was analyzed in detail. Based on the results of the study described in the article, restrictions arising from the nature of forensic activities in the use of the concept of discrediting speech strategy, which are not typical for research activities, were established.
39
Seidemann, Michael. "Forensic Audiology." Seminars in Hearing 15, no. 03 (August 1994): 243–50. http://dx.doi.org/10.1055/s-0028-1083771.
Full text
40
Volkova, Tatyana F. "Speech Activity of the Modern Forensic Orator (On the Material of Speeches in Debates)." Vestnik Tomskogo gosudarstvennogo universiteta, no. 444 (June 2019): 38–45. http://dx.doi.org/10.17223/15617793/444/4.
Full text
41
Lutsenko, Kh, A. Roman, S. Grigoryan, and V. Kocharyan. "Research on a voice changed by distortion." Theory and Practice of Forensic Science and Criminalistics 23, no. 1 (July 27, 2021): 188–202. http://dx.doi.org/10.32353/khrife.1.2021.14.
Full textAbstract:
The concept and essence of distortion are considered from a technical stand-point and criminal law perspective. The most common ways of distorting a voice and a speech are provided, as well as certain methods of detecting an intentional change in a voice and human speech by computer tools and linguistic analysis.
Some software and hardware tools changing a speech signal both in real time and in a pre-prepared recording are analyzed.
To solve diagnostic and identification tasks, a pressing issue in forensic video and audio analysis is studied which is addressed to forensic experts in this field more often.
42
Sarifuddin, Sarifuddin, Maknun Tadjuddin, and Ery Iswary. "A Hate and Provocative Speech Act in Social Media: A Forensic Linguistics Study." ELS Journal on Interdisciplinary Studies in Humanities 4, no. 3 (September 30, 2021): 363–68. http://dx.doi.org/10.34050/elsjish.v4i3.18196.
Full textAbstract:
This study aims to: (1) explain the types of provocative speech acts of Natalius Pigai on YouTube social media, (2) explain the forms of provocative speech acts on YouTube social media. The data in this study are languages that are supposed to contain provocative criminal acts on YouTube social media. The data source in this study is the social media YouTube. The method used in this research is descriptive qualitative method, data collection techniques in the form of viewing and documentation. The data were analyzed using the steps of (1) identifying, (2) classifying, and (3) analyzing. The results of this study indicate that: Natalis Pigai's utterances on social media contain literal indirect speech acts, while locutionary speech acts use declarative locutions, expressive illocutions, and get hearer to think about perlocutions (make the interlocutor think about). These statements violate the Criminal Code, Article 160 and Article 161 regarding sedition. Keywords: provocative speech acts, social media, forensic linguistics.
Keywords: provocative speech, social media, forensic linguistics.
43
Cimen, Kaan, Ilhan Otag, and Mehmet Cimen. "PTERION TYPES AND MORPHOMETRY IN MIDDLE AND SOUTH ANATOLIAN ADULT SKULLS. Tipos de pterión y morfometría en cráneos adultos de Anatolia media y sur." Revista Argentina de Anatomía Clínica 11, no. 1 (March 24, 2019): 8–17. http://dx.doi.org/10.31051/1852.8023.v11.n1.21637.
Full textAbstract:
Pterion is an irregular H letter shaped sutural confluence in the temporal fossa formed by frontal, parietal bones, great wing of sphenoid bone and temporal squama. Pterion is classified in 4 types as follows: sphenoparietal, frontotemporal, epipteric and stellate. The pterion represents: anterior branch of the middle meningeal artery, middle cerebral artery, Broca’s motor speech area, insula and stem of the lateral cerebral sulcus. This pterion junction has been used as a common extra-cranial landmark for surgeons in microsurgical and surgical approaches pertaining to important pathologies of this region. In the present study, our aim was to determine pterion types, to estimate distances between pterion and some special landmarks by which means to contribute to the related literature by comparing the data with other studies focusing on various populations. Pterion types identified by observation and measurements were taken by steel Vernier caliper. This study was conducted with 75 adult skulls (both sides 150 pterion). Skulls were classified with regard to gender as: 47 male and 28 female. Pterion types observed in both genders were classified as: sphenoparietal type 82% (84.04% in male, 78.57% in female), frontotemporal type 4.66% (5.31% in male, 3.57% in female), epipteric type 10.66% (8.51% in male, 14.28% in female) and stellate type 2.66% (2.12% in male, 3.57% in female). These findings will be usefull for clinicians, anthropologists and forensics. El pterion es una confluencia sutural con forma de letra H irregular en la fosa temporal formada por los huesos frontales, parietales, el ala mayor del hueso esfenoides y la escama temporal. Pterion se clasifica en 4 tipos de la siguiente manera: Esfenoparietal, frontotemporal, epiptérico y estrellado. El pterion representa: la rama anterior de la arteria meníngea media, la arteria cerebral media, el área motora del habla de Broca, la ínsula y el vástago del surco cerebral lateral. Esta unión del pterión se ha utilizado como un hito extracraneal común para los cirujanos en enfoques microquirúrgicos y quirúrgicos relacionados con patologías importantes de esta región. En el presente estudio, nuestro objetivo es determinar los tipos de pterion, estimar las distancias entre el pterión y algunos puntos de referencia especiales para contribuir a la literatura relacionada mediante la comparación de los datos con otros estudios que se centran en diversas poblaciones. Los tipos de pterión identificados por observación y mediciones fueron tomados por un calibrador a Vernier de acero. Este estudio se realizó con 75 cráneos adultos (ambos lados 150 pterion). Los cráneos se clasifican en función del género como: 47 hombres y 28 mujeres. Los tipos de pterion observados en ambos sexos se clasifican en: tipo esfenoparietal 82% (84,04% en hombres, 78,57% en mujeres), tipo frontotemporal 4,66% (5,31% en hombres, 3,57% en mujeres), tipo epiptérico 10,66% (8,51% en hombres, 14,28% en mujeres) y tipo estrellado 2,66% (2,12% en hombres, 3,57% en mujeres). Estos hallazgos serán útiles para los clínicos, antropólogos y médicos forenses.
44
Sokolova, T. P. "TOPICAL ISSUES OF EXPERT DIAGNOSTICS OF THE AUTHOR’S CONCEPTUAL CHARACTERISTICS." Courier of Kutafin Moscow State Law University (MSAL)), no. 6 (July 31, 2020): 111–19. http://dx.doi.org/10.17803/2311-5998.2020.70.6.111-119.
Full textAbstract:
Within the school of forensic expertology, in the context of modern challenges of digitalization, the current problems of forensic and expert diagnostics are considered to establish the conceptual characteristics of the author of a speech product posted on the Internet, which has become a criminal environment. Based on the analysis of a number of provisions of traditional methods of author’s research of written speech (determining gender, age, profession, level of education, level of speech culture, native language of the author of an anonymous text), their inapplicability is revealed in the expert diagnosis of a modern language personality, which manifests itself mainly in a virtual environment. The author substantiates the need to develop a modern methodology for determining the conceptual characteristics of an anonymous author of a speech product within the competence of a speech expert based on the analysis of the corpus of modern web communication texts.
45
Herrera Martínez, Marcelo, Andrea Lorena Aldana Blanco, and Ana Maria Guzmán Palacios. "Speech pattern recognition for forensic acoustic purposes." TECCIENCIA 9, no. 17 (October 2014): 47–56. http://dx.doi.org/10.18180/tecciencia.2014.17.5.
Full text
46
Seery, Carol Hubbard. "Differential Diagnosis of Stuttering for Forensic Purposes." American Journal of Speech-Language Pathology 14, no. 4 (November 2005): 284–97. http://dx.doi.org/10.1044/1058-0360(2005/028).
Full textAbstract:
Purpose: This case study demonstrates the application of an assessment protocol for differential diagnosis of psychogenic stuttering, neurogenic stuttering, developmental stuttering, and malingering. Method: A male in his late 30s, accused of armed robbery, was evaluated for stuttering at the request of his defense attorney. The speech assessment included 4 main sections: collection of speech samples, observation in multiple speaking conditions, evaluation of communication attitudes, and consideration of case history and background information. Results: The defendant stuttered severely in all speaking conditions. He demonstrated typical stuttering loci and consistency, but no adaptation. Communication attitudes were typical of people who stutter, but steady, direct eye contact was atypical. His statements about his speech conflicted with reports of outside witnesses. Conclusions: Characteristics were consistent with developmental stuttering and partial malingering. Both psychogenic and neurogenic forms of stuttering were suspected, but mixed results were largely unsupportive. Valuable protocol elements included speech sampling under multiple speaking conditions, careful examination of case history information, and indirect tests of malingering. Further knowledge and research are warranted to improve processes of differential diagnoses among subtypes of developmental, psychogenic, and neurogenic forms of stuttering as well as malingering.
47
Brendel, O. "Modern possibilities of diagnostic research in the field of forensic video and audio analysis." Theory and Practice of Forensic Science and Criminalistics 23, no. 1 (July 27, 2021): 203–11. http://dx.doi.org/10.32353/khrife.1.2021.15.
Full textAbstract:
Issues that are increasingly arising in criminal proceedings are highlighted, namely: use of data obtained as a result of diagnostic researches on video, sound recordings that allows to ensure a higher level of completeness, objectivity and comprehensiveness of research. The purpose of the article is to analyze the possibilities of forensic diagnostic researches on video and sound recordings of both oral speech and the sound environment of an offense event.
Various modern possibilities of researches on video and sound recordings are considered. Attention is paid both to the specifics of diagnostic speech researches in order to obtain information about personality of the unknown speaker and to information that can be obtained through research and diagnosis of non-speech information. Analyzed the possibilities (within the framework of the examination of video, sound recording) diagnostic researches on directly speech information, including the definition of: oral speech form, nature of relations between the interlocutors, conversation meaning (definition of the meaningful situation: consent vs disagreement; permission vs prohibition; understanding vs misunderstanding; request; advice; promise; assurance; gratitude; threat; clarification; order; question; message, etc.), rate of speech and the emotional state of the interlocutors, as well as expert diagnostics of biological parameters of the speakers. Possibilities of diagnostic studies of technical studies of recording media and recording equipment, that can contain information about the technology of obtaining/fixing/saving video, sound recordings, properties and features of the media itself are considered. Non-speech sounds are classified according to their belonging to certain sources. The article highlights effectiveness of using the forensic information obtained through forensic examination in practice of investigating crimes.
48
Svankulov, A. "USE OF LINGUISTIC KNOWLEDGE IN FORENSIC EXPERTISE. COMPARATIVE ANALYSIS." Criminalistics and Forensics, no. 64 (May 7, 2019): 435–41. http://dx.doi.org/10.33994/kndise.2019.64.38.
Full textAbstract:
The article describes the use of linguistic and psychological knowledge in the forensic expert activity of the Republic of Kazakhstan as an independent form of complex psychological and philological research where experts who obtained knowledge in the field of psychology and philology take part. During the implementation of this type of research, research methods have been developed that are included in the State Register of Methods of Forensic Research of the Republic of Kazakhstan. In addition, the article states that further development of this area in forensic expert activities will contribute to the formation of a new type of research – Forensic Religious Expertise. The direct application of linguistic knowledge in conducting forensic expertises is subdivided into five areas, such as: expert examination of real works on charges of extremist activity, as well as on charges of violating racial, religious, national and social hate and hostility, linguistic examination of advertising texts and treaties, linguistic expert examination of trademarks, verbal study of crimes related to the propaganda of extremism and terrorism, in the investigation of corruption crimes, fraud, extortion. The article also shows the connection of the linguistic expertise with other types, for example, with a judicial video phonography examination, in case of the need for identification of the speaker by verbal speech on the phonogram under study, during the author’s examination for the authorship of the text, in the psychological and forensic expertise – for the solution of question of the learned speeches of the suspect, other persons during the interrogation, other investigative actions. The author presents the results of a comparative analysis of the use of linguistic knowledge abroad, in particular, in the UK. Its peculiarity is that linguistic research is carried out at scientific educational centers of the humanitarian orientation. The following directions in linguistic studies conducted in this country are considered: a) forensic authore-identification, the essence of which is the determining the authorship of oral or written text, individual characteristics of the author (age, way of life, religious and political views, nationality, gender, profession, etc., b) forensic phonetics which involves the use of phonetics and phonology – sections of linguistics, c) forensic stylistics aimed at solving issues related to the plagiarism of the semantic content of the texts, while the author states that in Kazakhstan the decision on this issue is assigned to the competence of authore-identification examination, d) discourse analysis as the most promising type of research at present, is connected with research of written, verbal text in combination with non-verbal means of communication (gestures, facial expressions). Key words: legal linguistics, discourse, psychological and philological examination, forensic authore-identification, products of speech activity, linguistic research, psychological research.
49
Lee, V. S., and R. D. Karymsakova. "LINGUISTIC PRAGMATICS AND SPEECH ACT THEORY AS A SCIENTIFIC METHOD OF JUDICIAL LINGUISTIC EXPERTISE (from lingual expert practice)." Bulletin of Kemerovo State University, no. 3 (July 28, 2016): 155–59. http://dx.doi.org/10.21603/2078-8975-2016-3-155-159.
Full textAbstract:
The paper reflects the progress and results of such applied linguistic research, as the conclusion of the expert-philologist (forensic linguistic) expertise, the object of which is due to the content of tasks for the specialist (expert). According to the transcript of a conversation, the features of verbal behavior of participants of the conversation that are relevant for the criminal investigation are studied. The study used lingual pragmatic analysis, techniques of text discursive analysis. The result of the semantic-pragmatic analysis of speech situations, speech acts as the units of researched conversation led to unambiguous conclusions about the nature of relations between the participants of the conversation, the communicative role of each of them, the absence of women’s guilt in the state of fear experienced by man, etc. In general, conversation analysis has shown that the achievement of linguistic pragmatics with its theory of speech acts can be successfully used in forensic linguistic examination. The results of this research can be used in the formulation of recommendations on the methodological support of forensic linguistic examination.
50
Kuznetsov, V. O. ""Provocation" as an Expert Term in Forensic Linguistics." Theory and Practice of Forensic Science 15, no. 3 (October 23, 2020): 6–18. http://dx.doi.org/10.30764/1819-2785-2020-3-6-18.
Full textAbstract:
The article addresses the category of “provocation” as a forensic term that is an interdisciplinary concept in between the legal legal and linguistic concepts of “provocation”. An expert term “speech provocation” has been developed through an expert analysis where the category of “provocation” has been considered from the legal, linguistic, and expert perspectives. As a part of the consideration of the concept in the expert aspect, the relationship between the legal and linguistic categories has been established. The author concluded that as an expert linguistic term in examinations in corruption cases, the term “speech provocation for an offer/payment of a bribe” is used. In this case, the speech provocation is interpreted as a verbal act which incites one of the communicators to commit an unlawful act – to bribe. That is the linguistic contents of the phenomenon legally called “crime provocation". The article also addresses the methodological aspect of the detection of speech provocation.