Artykuły w czasopismach: „Sound recognition”

1

Ishihara, Kazushi, Kazunori Komatani, Tetsuya Ogata i Hiroshi G. Okuno. "Sound-Imitation Word Recognition for Environmental Sounds". Transactions of the Japanese Society for Artificial Intelligence 20 (2005): 229–36. http://dx.doi.org/10.1527/tjsai.20.229.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

2

Okubo, Shota, Zhihao Gong, Kento Fujita i Ken Sasaki. "Recognition of Transient Environmental Sounds Based on Temporal and Frequency Features". International Journal of Automation Technology 13, nr 6 (5.11.2019): 803–9. http://dx.doi.org/10.20965/ijat.2019.p0803.

Pełny tekst źródła

Streszczenie:

Environmental sound recognition (ESR) refers to the recognition of all sounds other than the human voice or musical sounds. Typical ESR methods utilize spectral information and variation within it with respect to time. However, in the case of transient sounds, spectral information is insufficient because only an average quantity of a given signal within a time period can be recognized. In this study, the waveform of sound signals and their spectrum were analyzed visually to extract temporal characteristics of the sound more directly. Based on the observations, features such as the initial rise time, duration, and smoothness of the sound signal; the distribution and smoothness of the spectrum; the clarity of the sustaining sound components; and the number and interval of collisions in chattering were proposed. Experimental feature values were obtained for eight transient environmental sounds, and the distributions of the values were evaluated. A recognition experiment was conducted on 11 transient sounds. The Mel-frequency cepstral coefficient (MFCC) was selected as reference. A support vector machine was adopted as the classification algorithm. The recognition rates obtained from the MFCC were below 50% for five of the 11 sounds, and the overall recognition rate was 69%. In contrast, the recognition rates obtained using the proposed features were above 50% for all sounds, and the overall rate was 86%.

Style APA, Harvard, Vancouver, ISO itp.

3

Hanna, S. A., i Ann Stuart Laubstein. "Speaker‐independent sound recognition". Journal of the Acoustical Society of America 92, nr 4 (październik 1992): 2475–76. http://dx.doi.org/10.1121/1.404442.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

4

Ibrahim Alsaif, Omar, Kifaa Hadi Thanoon i Asmaa Hadi Al_bayati. "Auto electronic recognition of the Arabic letters sound". Indonesian Journal of Electrical Engineering and Computer Science 28, nr 2 (1.11.2022): 769. http://dx.doi.org/10.11591/ijeecs.v28.i2.pp769-776.

Pełny tekst źródła

Streszczenie:

In this research Arabic speech sounds have been studied and investigated, so as to find the distinctive features of each articulated sound. Therefore, certain Arabic sound which share certain approximate distinctive significant features have been chosen for study the ability of distinguishing among them through abstracting characteristic features for them. The signals of speech for the sounds have been recorded through the microphone which represented in a binary matrix. This procedure was implemented so as prepare these signals for processing operation through which two features for the co-occurrence matrix (contrast, energy) have been counted. The values of these features were studied and compared from one person to another to discover the certain speech sounds properties sharing certain common distinguishing features approximate in their articulation one another. The results analysis for this study gave the ability of the dependence to these features for distinguish the sound of speaker, in addition to the high ability which provided to distinguish among the arabic letters, where no connect between both co-occurrence matrix elements and the features of signaling of any arabic letters.

Style APA, Harvard, Vancouver, ISO itp.

5

Guo, Xuan, Yoshiyuki Toyoda, Huankang Li, Jie Huang, Shuxue Ding i Yong Liu. "Environmental Sound Recognition Using Time-Frequency Intersection Patterns". Applied Computational Intelligence and Soft Computing 2012 (2012): 1–6. http://dx.doi.org/10.1155/2012/650818.

Pełny tekst źródła

Streszczenie:

Environmental sound recognition is an important function of robots and intelligent computer systems. In this research, we use a multistage perceptron neural network system for environmental sound recognition. The input data is a combination of time-variance pattern of instantaneous powers and frequency-variance pattern with instantaneous spectrum at the power peak, referred to as a time-frequency intersection pattern. Spectra of many environmental sounds change more slowly than those of speech or voice, so the intersectional time-frequency pattern will preserve the major features of environmental sounds but with drastically reduced data requirements. Two experiments were conducted using an original database and an open database created by the RWCP project. The recognition rate for 20 kinds of environmental sounds was 92%. The recognition rate of the new method was about 12% higher than methods using only an instantaneous spectrum. The results are also comparable with HMM-based methods, although those methods need to treat the time variance of an input vector series with more complicated computations.

Style APA, Harvard, Vancouver, ISO itp.

6

Cheng, Xiefeng, Pengfei Wang i Chenjun She. "Biometric Identification Method for Heart Sound Based on Multimodal Multiscale Dispersion Entropy". Entropy 22, nr 2 (20.02.2020): 238. http://dx.doi.org/10.3390/e22020238.

Pełny tekst źródła

Streszczenie:

In this paper, a new method of biometric characterization of heart sounds based on multimodal multiscale dispersion entropy is proposed. Firstly, the heart sound is periodically segmented, and then each single-cycle heart sound is decomposed into a group of intrinsic mode functions (IMFs) by improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN). These IMFs are then segmented to a series of frames, which is used to calculate the refine composite multiscale dispersion entropy (RCMDE) as the characteristic representation of heart sound. In the simulation experiments I, carried out on the open heart sounds database Michigan, Washington and Littman, the feature representation method was combined with the heart sound segmentation method based on logistic regression (LR) and hidden semi-Markov models (HSMM), and feature selection was performed through the Fisher ratio (FR). Finally, the Euclidean distance (ED) and the close principle are used for matching and identification, and the recognition accuracy rate was 96.08%. To improve the practical application value of this method, the proposed method was applied to 80 heart sounds database constructed by 40 volunteer heart sounds to discuss the effect of single-cycle heart sounds with different starting positions on performance in experiment II. The experimental results show that the single-cycle heart sound with the starting position of the start of the first heart sound (S1) has the highest recognition rate of 97.5%. In summary, the proposed method is effective for heart sound biometric recognition.

Style APA, Harvard, Vancouver, ISO itp.

7

Norman-Haignere, Sam V., i Josh H. McDermott. "Sound recognition depends on real-world sound level". Journal of the Acoustical Society of America 139, nr 4 (kwiecień 2016): 2156. http://dx.doi.org/10.1121/1.4950385.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

8

Zhai, Xiu, Fatemeh Khatami, Mina Sadeghi, Fengrong He, Heather L. Read, Ian H. Stevenson i Monty A. Escabí. "Distinct neural ensemble response statistics are associated with recognition and discrimination of natural sound textures". Proceedings of the National Academy of Sciences 117, nr 49 (20.11.2020): 31482–93. http://dx.doi.org/10.1073/pnas.2005644117.

Pełny tekst źródła

Streszczenie:

The perception of sound textures, a class of natural sounds defined by statistical sound structure such as fire, wind, and rain, has been proposed to arise through the integration of time-averaged summary statistics. Where and how the auditory system might encode these summary statistics to create internal representations of these stationary sounds, however, is unknown. Here, using natural textures and synthetic variants with reduced statistics, we show that summary statistics modulate the correlations between frequency organized neuron ensembles in the awake rabbit inferior colliculus (IC). These neural ensemble correlation statistics capture high-order sound structure and allow for accurate neural decoding in a single trial recognition task with evidence accumulation times approaching 1 s. In contrast, the average activity across the neural ensemble (neural spectrum) provides a fast (tens of milliseconds) and salient signal that contributes primarily to texture discrimination. Intriguingly, perceptual studies in human listeners reveal analogous trends: the sound spectrum is integrated quickly and serves as a salient discrimination cue while high-order sound statistics are integrated slowly and contribute substantially more toward recognition. The findings suggest statistical sound cues such as the sound spectrum and correlation structure are represented by distinct response statistics in auditory midbrain ensembles, and that these neural response statistics may have dissociable roles and time scales for the recognition and discrimination of natural sounds.

Style APA, Harvard, Vancouver, ISO itp.

9

Song, Hang, Bin Zhao, Jun Hu, Haonan Sun i Zheng Zhou. "Research on Improved DenseNets Pig Cough Sound Recognition Model Based on SENets". Electronics 11, nr 21 (31.10.2022): 3562. http://dx.doi.org/10.3390/electronics11213562.

Pełny tekst źródła

Streszczenie:

In order to real-time monitor the health status of pigs in the process of breeding and to achieve the purpose of early warning of swine respiratory diseases, the SE-DenseNet-121 recognition model was established to recognize pig cough sounds. The 13-dimensional MFCC, ΔMFCC and Δ2MFCC were transverse spliced to obtain six groups of parameters that could reflect the static, dynamic and mixed characteristics of pig sound signals respectively, and the DenseNet-121 recognition model was used to compare the performance of the six sets of parameters to obtain the optimal set of parameters. The DenseNet-121 recognition model was improved by using the SENets attention module to enhance the recognition model's ability to extract effective features from the pig sound signals. The results showed that the optimal set of parameters was the 26-dimensional MFCC + ΔMFCC, and the rate of recognition accuracy, recall, precision and F1 score of the SE-DenseNet-121 recognition model for pig cough sounds were 93.8%, 98.6%, 97% and 97.8%, respectively. The above results can be used to develop a pig cough sound recognition system for early warning of pig respiratory diseases.

Style APA, Harvard, Vancouver, ISO itp.

10

Binh, Nguyen Dang. "Gestures Recognition from Sound Waves". EAI Endorsed Transactions on Context-aware Systems and Applications 3, nr 10 (12.09.2016): 151679. http://dx.doi.org/10.4108/eai.12-9-2016.151679.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

11

Casey, M. "MPEG-7 sound-recognition tools". IEEE Transactions on Circuits and Systems for Video Technology 11, nr 6 (czerwiec 2001): 737–47. http://dx.doi.org/10.1109/76.927433.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

12

She, Chen-Jun, i Xie-Feng Cheng. "Design framework of hybrid ensemble identification network and its application in heart sound analysis". AIP Advances 12, nr 4 (1.04.2022): 045117. http://dx.doi.org/10.1063/5.0083764.

Pełny tekst źródła

Streszczenie:

Mixed heart sounds include heart sounds in a state of resting and motion. The analysis of heart sound signals in a state of motion is a difficult problem. (1) First, the mixed heart sound signal was collected by using the shoulder-strap-type heart sound acquisition device designed and made by our research group. The acquisition scheme and data preprocessing method were given, and the characteristics of heart sound signals in a state of motion were analyzed. (2) The design framework of the Hybrid Ensemble Identification Network (HEINet) is proposed, and the design requirements, architecture principles, and detailed design steps are discussed. The design process is simple, fast, and convenient. (3) In this paper, according to the design framework of HEINet, HEINet of the mixed heart sound signal is designed, and the recognition rate of the mixed heart sound signal in biometric authentication has reached 99.1%. Based on this design framework, HEINet of the heart sound signal for the Heart Sounds Catania 2011 heart sound database and HEINet of the electrocardiogram signal for Massachusetts Institute of Technology-Beth Israel Hospital arrhythmia database were designed, and the recognition rates both met the expected requirements. It shows that the design framework of HEINet has obvious universality.

Style APA, Harvard, Vancouver, ISO itp.

13

Zhang, Sunan, Jianyan Tian, Amit Banerjee i Jiangli Li. "Automatic Recognition of Porcine Abnormalities Based on a Sound Detection and Recognition System". Transactions of the ASABE 62, nr 6 (2019): 1755–65. http://dx.doi.org/10.13031/trans.12975.

Pełny tekst źródła

Streszczenie:

Abstract. With the rapid development of large-scale breeding, manual long-term monitoring of the daily activities and health of livestock is costly and time-consuming. Therefore, the application of bio-acoustics to automatic monitoring has received increasing attention. Although bio-acoustical techniques have been applied to the recognition of animal sounds in many studies, there is a dearth of studies on the automatic recognition of abnormal sounds from farm animals. In this study, an automatic detection and recognition system based on bio-acoustics is proposed to hierarchically recognize abnormal animal states in a large-scale pig breeding environment. In this system, we extracted the mel-frequency cepstral coefficients (MFCC) and subband spectrum centroid (SSC) as composite feature parameters. At the first level, support vector data description (SVDD) is used to detect abnormal sounds in the acoustic data. At the second level, a back-propagation neural network (BPNN) is used to classify five kinds of abnormal sounds in pigs. Furthermore, improved spectral subtraction is developed to reduce the noise interference as much as possible. Experimental results show that the average detection accuracy and the average recognition accuracy of the proposed system are 94.2% and 95.4%, respectively. The effectiveness of the proposed sound detection and recognition system was also verified through tests at a pig farm. Keywords: Abnormal sounds, MFCC, SSC, States of pigs, SVDD.

Style APA, Harvard, Vancouver, ISO itp.

14

Tappero, Fabrizio, Rosa Alsina-Pagès, Leticia Duboc i Francesc Alías. "Leveraging Urban Sounds: A Commodity Multi-Microphone Hardware Approach for Sound Recognition". Proceedings 4, nr 1 (8.03.2019): 55. http://dx.doi.org/10.3390/ecsa-5-05756.

Pełny tekst źródła

Streszczenie:

City noise and sound are measured and processed with the purpose of drawing appropriate government legislation and regulations, ultimately aimed at contributing to a healthier environment for humans. The primary use of urban noise analysis is carried out with the main purpose of reporting or denouncing, to the appropriate authorities, a misconduct or correct a misuse of council resources. We believe that urban sounds carry more information than what it is extracted to date. In this paper we present a cloud-based urban sound analysis system for the capturing, processing and trading of urban sound-based information. By leveraging modern artificial intelligence algorithms running on a FOG computing city infrastructure, we will show how the presented solution can offer a valuable solution for exploiting urban sound information. A specific focus is given to the hardware implementation of the sound sensor and its multimicrophone architecture. We discuss how the presented architecture is designed to allow the trading of sound information between independent parties, transparently, using cloud-based sound processing APIs running on an inexpensive consumer-grade microphone.

Style APA, Harvard, Vancouver, ISO itp.

15

Dodd, Barbara, i Alex Carr. "Young Children’s Letter-Sound Knowledge". Language, Speech, and Hearing Services in Schools 34, nr 2 (kwiecień 2003): 128–37. http://dx.doi.org/10.1044/0161-1461(2003/011).

Pełny tekst źródła

Streszczenie:

Purpose: This study compares three essential skills in early literacy: letter-sound recognition, letter-sound recall, and letter reproduction. Previous research comparing these aspects of letter-sound knowledge is limited. Method: Eighty-three normally developing children between the ages of 4:11 (years:months) and 6:4 were asked to recognize (i.e., point to the appropriate letter when the letter’s sound is given), recall (i.e., say the letter’s sound), and reproduce (i.e., write the letter when the letter’s sound is given) 32 letter sounds. Results: The children performed better in letter-sound recognition than in letter-sound recall, and better in letter-sound recall than in letter reproduction. Girls performed no differently from boys. Younger children performed as well as older children. Socioeconomic status had significant influence on the level of development for all tasks. Clinical Implications: Clinicians and educators need to be aware of the different aspects of letter-sound knowledge development and how it can be assessed so that intervention can follow the normal developmental sequence of acquisition.

Style APA, Harvard, Vancouver, ISO itp.

16

ZHANG, WENYING, XINGMING GUO, ZHIHUI YUAN i XINGHUA ZHU. "HEART SOUND CLASSIFICATION AND RECOGNITION BASED ON EEMD AND CORRELATION DIMENSION". Journal of Mechanics in Medicine and Biology 14, nr 04 (3.07.2014): 1450046. http://dx.doi.org/10.1142/s0219519414500468.

Pełny tekst źródła

Streszczenie:

Analysis of heart sound is of great importance to the diagnosis of heart diseases. Most of the feature extraction methods about heart sound have focused on linear time-variant or time-invariant models. While heart sound is a kind of highly nonstationary and nonlinear vibration signal, traditional methods cannot fully reveal its essential properties. In this paper, a novel feature extraction approach is proposed for heart sound classification and recognition. The ensemble empirical mode decomposition (EEMD) method is used to decompose the heart sound into a finite number of intrinsic mode functions (IMFs), and the correlation dimensions of the main IMF components (IMF1~IMF4) are calculated as feature set. Then the classical Binary Tree Support Vector Machine (BT-SVM) classifier is employed to classify the heart sounds which include the normal heart sounds (NHSs) and three kinds of abnormal signals namely mitral stenosis (MT), ventricular septal defect (VSD) and aortic stenosis (AS). Finally, the performance of the new feature set is compared with the correlation dimensions of original signals and the main IMF components obtained by the EMD method. The results showed that, for NHSs, the feature set proposed in this paper performed the best with recognition rate of 98.67%. For the abnormal signals, the best recognition rate of 91.67% was obtained. Therefore, the proposed feature set is more superior to two comparative feature sets, which has potential application in the diagnosis of cardiovascular diseases.

Style APA, Harvard, Vancouver, ISO itp.

17

Tsai, Wen-Chung, You-Jyun Shih i Nien-Ting Huang. "Hardware-Accelerated, Short-Term Processing Voice and Nonvoice Sound Recognitions for Electric Equipment Control". Electronics 8, nr 9 (23.08.2019): 924. http://dx.doi.org/10.3390/electronics8090924.

Pełny tekst źródła

Streszczenie:

We proposed and implemented a sound recognition system for electric equipment control. In recent years, industry 4.0 has propelled a rapid growth in intelligent human–machine interactions. User acoustic voice commands for machine control have been examined the most by researchers. The targeted machine can be controlled through voice without the use of any hand-held device. However, compared with human voice recognition, limited research has been conducted on nonhuman voice (e.g., mewing sounds) or nonvoice sound recognition (e.g., clapping). Processing of such short-term, biometric nonvoice sounds for electric equipment control requires a rapid response with correct recognition. In practice, this could lead to a trade-off between recognition accuracy and processing performance for conventional software-based implementations. Therefore, we realized a field-programmable gate array-based embedded system, such a hardware-accelerated platform, can enhance information processing performance using a dynamic time warping accelerator. Furthermore, information processing was refined for two specific applications (i.e., mewing sounds and clapping) to enhance system performance including recognition accuracy and execution speed. Performance analyses and demonstrations on real products were conducted to validate the proposed system.

Style APA, Harvard, Vancouver, ISO itp.

18

Zhang, Ke, Yu Su, Jingyu Wang, Sanyu Wang i Yanhua Zhang. "Environment Sound Classification System Based on Hybrid Feature and Convolutional Neural Network". Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University 38, nr 1 (luty 2020): 162–69. http://dx.doi.org/10.1051/jnwpu/20203810162.

Pełny tekst źródła

Streszczenie:

At present, the environment sound recognition system mainly identifies environment sounds with deep neural networks and a wide variety of auditory features. Therefore, it is necessary to analyze which auditory features are more suitable for deep neural networks based ESCR systems. In this paper, we chose three sound features which based on two widely used filters:the Mel and Gammatone filter banks. Subsequently, the hybrid feature MGCC is presented. Finally, a deep convolutional neural network is proposed to verify which features are more suitable for environment sound classification and recognition tasks. The experimental results show that the signal processing features are better than the spectrogram features in the deep neural network based environmental sound recognition system. Among all the acoustic features, the MGCC feature achieves the best performance than other features. Finally, the MGCC-CNN model proposed in this paper is compared with the state-of-the-art environmental sound classification models on the UrbanSound 8K dataset. The results show that the proposed model has the best classification accuracy.

Style APA, Harvard, Vancouver, ISO itp.

19

Xu, Hui Hong, i Su Chun Gao. "Speaker Recognition Study Based on Optimized Baum-Welch Algorithm". Applied Mechanics and Materials 543-547 (marzec 2014): 2471–73. http://dx.doi.org/10.4028/www.scientific.net/amm.543-547.2471.

Pełny tekst źródła

Streszczenie:

The speaker recognition is a sort of biological recognition technology according to person's sound to identify .The article based on vc platform implement speaker recognitions function using VQ and HMM technology. using genetic algorithm to improve the Baum-Welch algorithm.Trough experiment verificate that improved-arithmetic enhance recognition effect.

Style APA, Harvard, Vancouver, ISO itp.

20

Cai, Rui, Qian Wang, Yucheng Hou i Haorui Liu. "Event Monitoring of Transformer Discharge Sounds based on Voiceprint". Journal of Physics: Conference Series 2078, nr 1 (1.11.2021): 012066. http://dx.doi.org/10.1088/1742-6596/2078/1/012066.

Pełny tekst źródła

Streszczenie:

Abstract This paper investigates the operation inspection and anomaly diagnosis of transformers in substations, and carries out an application study of artificial intelligence-based sound recognition technology in transformer discharge diagnosis to improve the timeliness and diagnostic capability of intelligent monitoring of substation equipment operation. In this study, a sound parameterization technology in the field of sound recognition is used to implement automatic discharge sound detections. The sound samples are pre-processed and then Mel-frequency cepstrum coefficients (MFCCs) are extracted as features, which are used to train Gaussian mixture models (GMMs). Finally, the trained GMMs are used to detect discharge sounds in the place of transformers in substations. The test results demonstrate that the audio anomaly detection based on MFCCs and GMMs can be used to effectively recognize anomalous discharge in the high scenario of transformers.

Style APA, Harvard, Vancouver, ISO itp.

21

Darwin, C. J. "Listening to speech in the presence of other sounds". Philosophical Transactions of the Royal Society B: Biological Sciences 363, nr 1493 (7.09.2007): 1011–21. http://dx.doi.org/10.1098/rstb.2007.2156.

Pełny tekst źródła

Streszczenie:

Although most research on the perception of speech has been conducted with speech presented without any competing sounds, we almost always listen to speech against a background of other sounds which we are adept at ignoring. Nevertheless, such additional irrelevant sounds can cause severe problems for speech recognition algorithms and for the hard of hearing as well as posing a challenge to theories of speech perception. A variety of different problems are created by the presence of additional sound sources: detection of features that are partially masked, allocation of detected features to the appropriate sound sources and recognition of sounds on the basis of partial information. The separation of sounds is arousing substantial attention in psychoacoustics and in computer science. An effective solution to the problem of separating sounds would have important practical applications.

Style APA, Harvard, Vancouver, ISO itp.

22

Petrović, Milena, Gordana Ačić i Vera Milanković. "Sound of picture vs picture of sound: Musical palindrome". New Sound, nr 50-2 (2017): 217–28. http://dx.doi.org/10.5937/newso1750217p.

Pełny tekst źródła

Streszczenie:

This study investigated whether and how the musical palindrome (tonal, melodic, and metric) can be recognized in auditory and/or visual perception in musically trained participants. According to the results, we suggest that palindrome recognition can only be aurally perceived if it is short enough and the listener is quite sophisticated. There is a fair amount of research on the recognition of transformed auditory and visual patterns, as well as the visual symmetry perception in persons with ASD. Thus, a future study will test more people with ASD, on one hand, and musically trained participants recognizing short musical palindromes.

Style APA, Harvard, Vancouver, ISO itp.

23

Wu, Xuan, Silong Zhou, Mingwei Chen, Yihang Zhao, Yifei Wang, Xianmeng Zhao, Danyang Li i Haibo Pu. "Combined spectral and speech features for pig speech recognition". PLOS ONE 17, nr 12 (1.12.2022): e0276778. http://dx.doi.org/10.1371/journal.pone.0276778.

Pełny tekst źródła

Streszczenie:

The sound of the pig is one of its important signs, which can reflect various states such as hunger, pain or emotional state, and directly indicates the growth and health status of the pig. Existing speech recognition methods usually start with spectral features. The use of spectrograms to achieve classification of different speech sounds, while working well, may not be the best approach for solving such tasks with single-dimensional feature input. Based on the above assumptions, in order to more accurately grasp the situation of pigs and take timely measures to ensure the health status of pigs, this paper proposes a pig sound classification method based on the dual role of signal spectrum and speech. Spectrograms can visualize information about the characteristics of the sound under different time periods. The audio data are introduced, and the spectrogram features of the model input as well as the audio time-domain features are complemented with each other and passed into a pre-designed parallel network structure. The network model with the best results and the classifier were selected for combination. An accuracy of 93.39% was achieved on the pig speech classification task, while the AUC also reached 0.99163, demonstrating the superiority of the method. This study contributes to the direction of computer vision and acoustics by recognizing the sound of pigs. In addition, a total of 4,000 pig sound datasets in four categories are established in this paper to provide a research basis for later research scholars.

Style APA, Harvard, Vancouver, ISO itp.

24

Rosyadi, Naila Nabila, i Nur Hastuti. "Contrastive Analysis of Onomatopoeic Use in Nursery Rhymes as Children’s Environmental Sounds Recognition in Japanese and Indonesian". E3S Web of Conferences 359 (2022): 03014. http://dx.doi.org/10.1051/e3sconf/202235903014.

Pełny tekst źródła

Streszczenie:

Nursery rhymes play a role in children’s language development and help them recognize and express the environmental sounds or sounds around them. Onomatopoeia or imitation words are often found in nursery rhymes. Every country has a different language, so it has different phonetic sounds to express onomatopoeia. In this research, the author will contrast the onomatopoeic use in Japanese and Indonesian nursery rhymes. The theory and classification of onomatopoeia used in this research are combinations proposed by Akimoto (2002) and Kaneda (1978). This qualitative research used the listening and note-taking methods from Youtube videos. The analysis data used in this research are the referential matching method. The result from the research data shows that in Japanese nursery rhymes, onomatopoeia is the sound of nature, the sound from an object, the sound of a human, the sound of an animal, object condition, object movement, human movement, animal movement, and human emotion are found. Meanwhile, in Indonesian nursery rhymes found, almost all types of onomatopoeia in Japanese are found except for the class of the sound of a human, object movement, and human emotion are not found.

Style APA, Harvard, Vancouver, ISO itp.

25

Zhao, Huimin, Xianglin Huang, Wei Liu i Lifang Yang. "Environmental sound classification based on feature fusion". MATEC Web of Conferences 173 (2018): 03059. http://dx.doi.org/10.1051/matecconf/201817303059.

Pełny tekst źródła

Streszczenie:

With deep great breakthroughs of deep learning in the field of computer vision, the field of audio recognition has gradually introduced deep learning methods and achieved excellent results. These results are mainly for speech and music recognition research, and there is very little research on environmental sound classification. In recent years, people have begun to expand the research object of deep learning to the environmental sound, and achieved certain results. In this paper, we use ESC-50 as our test set, based on the SoundNet network and EnvNet network to propose a feature fusion method[1]. After the features extracted by SoundNet and EnvNet were merged, they were classified using fusion features. Experimental results show that this method has better classification accuracy for the recognition of environmental sounds than using either of the two networks separately for classification.

Style APA, Harvard, Vancouver, ISO itp.

26

Traer, James, Sam V. Norman-Haignere i Josh H. McDermott. "Causal inference in environmental sound recognition". Cognition 214 (wrzesień 2021): 104627. http://dx.doi.org/10.1016/j.cognition.2021.104627.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

27

R, Mrs Deepa. "Sound Recognition Using Recurrent Neural Network". International Journal for Research in Applied Science and Engineering Technology 6, nr 4 (30.04.2018): 815–19. http://dx.doi.org/10.22214/ijraset.2018.4137.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

28

Ntalampiras, Stavros. "Generalized Sound Recognition in Reverberant Environments". Journal of the Audio Engineering Society 67, nr 10 (25.10.2019): 772–81. http://dx.doi.org/10.17743/jaes.2019.0030.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

29

Beuter, Karl, i Rainer Weiß. "Sound pattern recognition supports automatic inspection". Sensor Review 5, nr 1 (styczeń 1985): 13–17. http://dx.doi.org/10.1108/eb007654.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

30

Marley, John. "System and method for sound recognition". Journal of the Acoustical Society of America 79, nr 1 (styczeń 1986): 207. http://dx.doi.org/10.1121/1.393586.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

31

Van Hedger, Stephen C., Howard C. Nusbaum, Shannon L. M. Heald, Alex Huang, Hiroki P. Kotabe i Marc G. Berman. "The Aesthetic Preference for Nature Sounds Depends on Sound Object Recognition". Cognitive Science 43, nr 5 (maj 2019): e12734. http://dx.doi.org/10.1111/cogs.12734.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

32

Cheng, Xie Feng, Ye Wei Tao i Zheng Jiang Huang. "Heart Sound Recognition - A Prospective Candidate for Biometric Identification". Advanced Materials Research 225-226 (kwiecień 2011): 433–36. http://dx.doi.org/10.4028/www.scientific.net/amr.225-226.433.

Pełny tekst źródła

Streszczenie:

Based on principles of human heart auscultation and the associated signal processing technology, we designed and manufactured "a double-header two-way voice auscultation detection device". The paper introduced a special human feature extraction method which is based on improved circle convolution (ICC) slicing algorithm combined with independent sub-band function (ISF). Follow we adopt a fire-new classification technology namely s1 and s2 model which is through two recognition steps to get different human’s heart sound features to assure validity, and then use similarity distance to carry out human heart sound pattern matching. The method was verified using 10 recorded heart sounds. The results show that identification accuracy is 85.7% in the two-step mode, and the error acceptance rate is less than 7%，and refusing error rate is less than 10% for normal people.

Style APA, Harvard, Vancouver, ISO itp.

33

Sudheer, D. "Audio Classification for Noise Filtering Using Convolutional Neural Network Approach". International Journal for Research in Applied Science and Engineering Technology 9, nr VII (31.07.2021): 3675–80. http://dx.doi.org/10.22214/ijraset.2021.37218.

Pełny tekst źródła

Streszczenie:

In each part of daily routine, sound assumes a significant part. From discrete security features to basic reconnaissance, a sound is a vivacious component to create automated frameworks for these fields. Scarcely any frameworks are now on the lookout, yet their effectiveness is a concerned point for their execution, real-time conditions. The learning capacities of Deep learning designs can be utilized to create sound characterization frameworks increase the impact of sound classification. Our main aim in this paper is to implement deep learning networks for filtering the nose and arrangement of these sound created by the natural phenomenon’s according to the spectrograms that are created accordingly. The spectrograms of these natural sounds are utilized for the preparation of the Convolutional neural network (CNN) and Tensor Deep Stacking Network (TDSN). The utilized datasets for analysis and creation of the networks are ESC-10 and ESC-50. These frameworks produced from these datasets were efficient in accomplishment of filtering the audio and recognizing the audio of the natural sound. The precision obtained from the developed system is 80% for CNN and 70% for TDSN. Form the implemented framework, it is presumed that proposed approach for sound filtering and recognition through the utility spectrogram of their subsequent sounds can be productively used to create efficient frameworks for audio classification and recognition based on neural networks.

Style APA, Harvard, Vancouver, ISO itp.

34

Sliwinska, Magdalena W., Alyson James i Joseph T. Devlin. "Inferior Parietal Lobule Contributions to Visual Word Recognition". Journal of Cognitive Neuroscience 27, nr 3 (marzec 2015): 593–604. http://dx.doi.org/10.1162/jocn_a_00721.

Pełny tekst źródła

Streszczenie:

This study investigated how the left inferior parietal lobule (IPL) contributes to visual word recognition. We used repetitive TMS to temporarily disrupt neural information processing in two anatomical fields of the IPL, namely, the angular (ANG) and supramarginal (SMG) gyri, and observed the effects on reading tasks that focused attention on either the meaning or sounds of written words. Relative to no TMS, stimulation of the left ANG selectively slowed responses in the meaning, but not sound, task, whereas stimulation of the left SMG affected responses in the sound, but not meaning, task. These results demonstrate that ANG and SMG doubly dissociate in their contributions to visual word recognition. We suggest that this functional division of labor may be understood in terms of the distinct patterns of cortico-cortical connectivity resulting in separable functional circuits.

Style APA, Harvard, Vancouver, ISO itp.

35

Endo, Hiroshi, Hidekazu Kaneko, Shuichi Ino i Waka Fujisaki. "An Attempt to Improve Food/Sound Congruity Using an Electromyogram Pseudo-Chewing Sound Presentation System". Journal of Advanced Computational Intelligence and Intelligent Informatics 21, nr 2 (15.03.2017): 342–49. http://dx.doi.org/10.20965/jaciii.2017.p0342.

Pełny tekst źródła

Streszczenie:

Improving the texture of foods provided during nursing care is necessary to improve the appetite of elderly individuals. We developed a system to vary perceived food texture using pseudo-chewing sounds generated from electromyogram (EMG) signals. However, this previous system could not provide chewing sounds that were sufficiently congruous with foods. Because food/sound combinations that seem unnatural cause individuals to feel uncomfortable with pseudo-chewing sounds, food/sound congruity is important. This research aims to improve the derivation and presentation of pseudo-chewing sounds so as to be able to provide various kinds of chewing sounds. The developed system adjusts the volume of pseudo-chewing sounds that are stored in a digital audio player based on the amplitude of the EMG signal envelope. Using this system, food/sound congruity was examined with two kinds of softened Japanese pickles. Six kinds of pseudo-chewing sounds were tested (noisy chewing sound, EMG chewing sound, and four kinds of actual chewing sounds: rice cracker, cookie, and two kinds of Japanese pickles). Participants reported that food/sound combinations were unnatural with the noisy and EMG chewing sounds, whereas the combinations felt more natural with the pseudo-chewing sounds of Japanese pickles. We concluded that the newly developed system could effectively reduce the unnatural feeling of food/sound incongruity.

Style APA, Harvard, Vancouver, ISO itp.

36

Evain, Solène, Benjamin Lecouteux, Didier Schwab, Adrien Contesse, Antoine Pinchaud i Nathalie Henrich Bernardoni. "Human beatbox sound recognition using an automatic speech recognition toolkit". Biomedical Signal Processing and Control 67 (maj 2021): 102468. http://dx.doi.org/10.1016/j.bspc.2021.102468.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

37

Di, Nayan, Muhammad Zahid Sharif, Zongwen Hu, Renjie Xue i Baizhong Yu. "Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification". PeerJ 11 (26.01.2023): e14696. http://dx.doi.org/10.7717/peerj.14696.

Pełny tekst źródła

Streszczenie:

Background Bee colony sound is a continuous, low-frequency buzzing sound that varies with the environment or the colony’s behavior and is considered meaningful. Bees use sounds to communicate within the hive, and bee colony sounds investigation can reveal helpful information about the circumstances in the colony. Therefore, one crucial step in analyzing bee colony sounds is to extract appropriate acoustic feature. Methods This article uses VGGish (a visual geometry group—like audio classification model) embedding and Mel-frequency Cepstral Coefficient (MFCC) generated from three bee colony sound datasets, to train four machine learning algorithms to determine which acoustic feature performs better in bee colony sound recognition. Results The results showed that VGGish embedding performs better than or on par with MFCC in all three datasets.

Style APA, Harvard, Vancouver, ISO itp.

38

Chen, Hao, Chengju Liu i Qijun Chen. "Efficient and robust approaches for three-dimensional sound source recognition and localization using humanoid robots sensor arrays". International Journal of Advanced Robotic Systems 17, nr 4 (1.07.2020): 172988142094135. http://dx.doi.org/10.1177/1729881420941357.

Pełny tekst źródła

Streszczenie:

Efficient and robust sound source recognition and localization is one of the basic techniques for humanoid robots in terms of reaction to environments. Due to the fixed sensor arrays and limited computation resources in humanoid robots, there comes challenge for sound source recognition and localization. This article proposes a sound source recognition and localization framework to realize real-time and precise sound source recognition and localization system using humanoid robots’ sensor arrays. The type of the audio is recognized according to the cross-correlation function. And steered response power-phase transform function in discrete angle space is used to search the sound source direction. The sound source recognition and localization framework presents a new multi-robots collaboration system to get the precise three-dimensional sound source position and introduces a distance weighting revision way to optimize the localization performance. Additionally, the experiment results carried out on humanoid robot NAO demonstrate that the proposed approaches can recognize and localize the sound source efficiently and robustly.

Style APA, Harvard, Vancouver, ISO itp.

39

Denys, Sam, Jan De Laat, Wouter Dreschler, Michael Hofmann, Astrid van Wieringen i Jan Wouters. "Language-Independent Hearing Screening Based on Masked Recognition of Ecological Sounds". Trends in Hearing 23 (styczeń 2019): 233121651986656. http://dx.doi.org/10.1177/2331216519866566.

Pełny tekst źródła

Streszczenie:

A language-independent automated self-test on tablet based on masked recognition of ecological sounds, the Sound Ear Check (SEC), was developed. In this test, 24 trials of eight different sounds are randomly presented in a noise that was spectrally shaped according to the average frequency spectra of the stimulus sounds, using a 1-up 2-down adaptive procedure. The test was evaluated in adults with normal hearing and hearing loss, and its feasibility was investigated in young children, who are the target population of this test. Following equalization of perceptual difficulty across sounds by applying level adjustments to the individual tokens, a reference curve with a steep slope of 18%/dB was obtained, resulting in a test with a high test–retest reliability of 1 dB. The SEC sound reception threshold was significantly associated with the averaged pure tone threshold ( r = .70), as well as with the speech reception threshold for the Digit Triplet Test ( r = .79), indicating that the SEC is susceptible to both audibility and signal-to-noise ratio loss. Sensitivity and specificity values on the order of magnitude of ∼70% and ∼80% to detect individuals with mild and moderate hearing loss, respectively, and ∼80% to detect individuals with slight speech-in-noise recognition difficulties were obtained. Homogeneity among sounds was verified in children. Psychometric functions fitted to the data indicated a steep slope of 16%/dB, and test–retest reliability of sound reception threshold estimates was 1.3 dB. A reference value of −9 dB signal-to-noise ratio was obtained. Test duration was around 6 minutes, including training and acclimatization.

Style APA, Harvard, Vancouver, ISO itp.

40

Perreau, Ann E., Richard S. Tyler, Victoria Frank, Alexandra Watts i Patricia C. Mancini. "Use of a Smartphone App for Cochlear Implant Patients With Tinnitus". American Journal of Audiology 30, nr 3 (10.09.2021): 676–87. http://dx.doi.org/10.1044/2021_aja-20-00195.

Pełny tekst źródła

Streszczenie:

Purpose Smartphone apps for tinnitus relief are now emerging; however, research supporting their use and effectiveness is lacking. Research has shown that Tinnitus Therapy sounds intended for individuals with acoustic hearing provide relief to some patients using cochlear implants (CIs) with tinnitus. Here, we evaluated the use and acceptability of a smartphone app to help CI patients with tinnitus. Method Participants completed a laboratory trial ( n = 19) and an at-home trial ( n = 14) using the ReSound Tinnitus Relief app to evaluate its acceptability and effectiveness in reducing their tinnitus. During the laboratory trial, participants selected a sound that was most acceptable in managing their tinnitus (termed chosen sound ). Word recognition scores in quiet were obtained before and after sound therapy. Participants were randomly assigned to one of two groups for the at-home trial, that is, AB or BA, using (A) the chosen sound for 2 weeks and (B) the study sound (i.e., broadband noise at hearing threshold) for another 2 weeks. Ratings were collected weekly to determine acceptability and effectiveness of the app in reducing tinnitus loudness and annoyance. Results Results indicated that some, but not all, participants found their chosen sound to be acceptable and/or effective in reducing their tinnitus. A majority of the participants rated the chosen sound or the study sound to be acceptable in reducing their tinnitus. Word recognition scores for most participants were not adversely affected using the chosen sound; however, a significant decrease was observed for three participants. All 14 participants had a positive experience with the app during the at-home trial on tests of sound therapy acceptability, effectiveness, and word recognition. Conclusions Sound therapy using a smartphone app can be effective for many tinnitus patients using CIs. Audiologists should recommend a sound and a level for tinnitus masking that do not interfere with speech perception.

Style APA, Harvard, Vancouver, ISO itp.

41

DEBBAL, S. M., i F. BEREKSI-REGUIG. "COMPARISON BETWEEN DISCRETE AND PACKET WAVELET TRANSFORM ANALYSES IN THE STUDY OF HEARTBEAT CARDIAC SOUNDS". Journal of Mechanics in Medicine and Biology 07, nr 02 (czerwiec 2007): 199–214. http://dx.doi.org/10.1142/s021951940700225x.

Pełny tekst źródła

Streszczenie:

This work investigates the study of heartbeat cardiac sounds through time–frequency analysis by using the wavelet transform method. Heart sounds can be utilized more efficiently by medical doctors when they are displayed visually rather through a conventional stethoscope. Heart sounds provide clinicians with valuable diagnostic and prognostic information. Although heart sound analysis by auscultation is convenient as a clinical tool, heart sound signals are so complex and nonstationary that they are very difficult to analyze in the time or frequency domain. We have studied the extraction of features from heart sounds in the time–frequency (TF) domain for the recognition of heart sounds through TF analysis. The application of wavelet transform (WT) for heart sounds is thus described. The performances of discrete wavelet transform (DWT) and wavelet packet transform (WP) are discussed in this paper. After these transformations, we can compare normal and abnormal heart sounds to verify the clinical usefulness of our extraction methods for the recognition of heart sounds.

Style APA, Harvard, Vancouver, ISO itp.

42

Yang, Haoping, Chunlin Yue, Cenyi Wang, Aijun Wang, Zonghao Zhang i Li Luo. "Effect of Target Semantic Consistency in Different Sequence Positions and Processing Modes on T2 Recognition: Integration and Suppression Based on Cross-Modal Processing". Brain Sciences 13, nr 2 (16.02.2023): 340. http://dx.doi.org/10.3390/brainsci13020340.

Pełny tekst źródła

Streszczenie:

In the rapid serial visual presentation (RSVP) paradigm, sound affects participants’ recognition of targets. Although many studies have shown that sound improves cross-modal processing, researchers have not yet explored the effects of sound semantic information with respect to different locations and processing modalities after removing sound saliency. In this study, the RSVP paradigm was used to investigate the difference between attention under conditions of consistent and inconsistent semantics with the target (Experiment 1), as well as the difference between top-down (Experiment 2) and bottom-up processing (Experiment 3) for sounds with consistent semantics with target 2 (T2) at different sequence locations after removing sound saliency. The results showed that cross-modal processing significantly improved attentional blink (AB). The early or lagged appearance of sounds consistent with T2 did not affect participants’ judgments in the exogenous attentional modality. However, visual target judgments were improved with endogenous attention. The sequential location of sounds consistent with T2 influenced the judgment of auditory and visual congruency. The results illustrate the effects of sound semantic information in different locations and processing modalities.

Style APA, Harvard, Vancouver, ISO itp.

43

Aveyard, Mark E. "Some consonants sound curvy: Effects of sound symbolism on object recognition". Memory & Cognition 40, nr 1 (26.09.2011): 83–92. http://dx.doi.org/10.3758/s13421-011-0139-3.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

44

ISHII, Yuki, i Shinichiro NISHIDA. "A study on hammering sound discrimination system with sound pattern recognition". Proceedings of Conference of Chugoku-Shikoku Branch 2017.55 (2017): K1315. http://dx.doi.org/10.1299/jsmecs.2017.55.k1315.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

45

Kim, Woo-Jun, Young-Sub Kim i Gwang-Seok Lee. "Sound recognition and tracking system design using robust sound extraction section". Journal of the Korea institute of electronic communication sciences 11, nr 8 (31.08.2016): 759–66. http://dx.doi.org/10.13067/jkiecs.2016.11.8.759.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

46

He, Aijun. "Application of Artificial Intelligence Elements and Multimedia Technology in the Optimization and Innovation of Teaching Mode of Animation Sound Production". Wireless Communications and Mobile Computing 2022 (27.02.2022): 1–14. http://dx.doi.org/10.1155/2022/3686643.

Pełny tekst źródła

Streszczenie:

Nowadays, with the rapid development of multimedia technology and computer information processing, the data of multimedia information presents explosive growth. At present, the method of using artificial recognition of sound materials is inefficient, and an automatic recognition and classification system of sound materials is needed. To improve the accuracy of sound recognition, two algorithm models are established to identify and compare the sound materials, which are the hidden Markov model (HMM) and back propagation neural network (BPNN) model. Firstly, HMM is established, and the sound material is randomly selected as the test sample. The comparison between the expected classification and the actual is tested, and the recognition rate of each classification is got. The final average recognition rate is 61%. The anti-interference characteristics of the training HMM are tested, and the identification rate of the training model is selected in 6 types of signal-to-noise ratio (SNR) environments. The recognition rate of the training model has an obvious downward trend with the decrease of the SNR. Secondly, the BPNN model is built, and 200 BPNN training experiments are conducted. The training model with the highest average recognition rate is selected as the experimental model. The average recognition rate of the final model is higher than 90%. The expression ability and stability of the trained model are simulated after the new sample is introduced, and the anti-interference performance of the model is tested in different environments of SNR. The results of performance test are good, and only the recognition rate of complex types of some sound sources decreased. Finally, the accuracy of the HMM in the experiment is not as high as that obtained by BPNN. Therefore, the training method of BPNN has a greater advantage in both recognition accuracy and recognition efficiency for the studied sound. It provides a reference for automatic recognition of sound materials.

Style APA, Harvard, Vancouver, ISO itp.

47

V. Chitre, Abhijit, Ketan J. Raut, Tushar Jadhav, Minal S. Deshmukh i Kirti Wanjale. "Hybrid Feature Based Classifier Performance Evaluation of Monophonic and Polyphonic Indian Classical Instruments Recognition". Journal of University of Shanghai for Science and Technology 23, nr 11 (2.11.2021): 879–90. http://dx.doi.org/10.51201/jusst/21/11969.

Pełny tekst źródła

Streszczenie:

Instrument recognition in computer music is an important research area that deals with sound modelling. Musical sounds comprises of five prominent constituents which are Pitch, timber, loudness, duration, and spatialization. The tonal sound is function of all these components playing critical role in deciding quality. The first four parameters can be modified, but timbre remains a challenge [6]. Then, inevitably, timbre became the focus of this piece. It is a sound quality that distinguishes one musical instrument from another, regardless of pitch or volume, and it is critical. Monophonic and polyphonic recordings of musical instruments can be identified using this method. To evaluate the proposed approach, three Indian instruments were experimented to generate training data set. Flutes, harmoniums, and sitars are among the instruments used. Indian musical instruments classify sounds using statistical and spectral parameters. The hybrid features from different domains extracting important characteristics from musical sounds are extracted. An Indian Musical Instrument SVM and GMM classifier demonstrate their ability to classify accurately. Using monophonic sounds, SVM and Polyphonic produce an average accuracy of 89.88% and 91.10%, respectively. According to the results of the experiments, GMM outperforms SVM in monophonic recordings by a factor of 96.33 and polyphonic recordings by a factor of 93.33.

Style APA, Harvard, Vancouver, ISO itp.

48

Schumacher, Federico, Vicente Espinoza, Francisca Mardones, Rodrigo Vergara, Alberto Aránguiz i Valentina Aguilera. "Perceptual Recognition of Sound Trajectories in Space". Computer Music Journal 45, nr 1 (2021): 39–54. http://dx.doi.org/10.1162/comj_a_00593.

Pełny tekst źródła

Streszczenie:

Abstract Sound spatialization is a technique used in various musical genres as well as in soundtrack production for films and video games. In this context, specialized software has been developed for the design of sound trajectories we have classified as (1) basic movements, or image schemas of spatial movement; and (2) archetypal geometric figures. Our contribution is to reach an understanding of how we perceive the movement of sound in space as a result of the interaction between an agent's or listener's sensory-motor characteristics and the morphological characteristics of the stimuli and the acoustic space where such interaction occurs. An experiment was designed involving listening to auditory stimuli and associating them with the aforementioned spatial movement categories. The results suggest that in most cases, the ability to recognize moving sound is hindered when there are no visual stimuli present. Moreover, they indicate that archetypal geometric figures are rarely perceived as such and that the perception of sound movements in space can be organized into three spatial dimensions—height, depth, and width—which the literature on sound localization also confirms.

Style APA, Harvard, Vancouver, ISO itp.

49

G, K. Krisna, I. Gusti Agung Widagda i Komang Ngurah Suarbawa. "Human Voice Recognition by Using Hebb Artificial Neural Network Method". BULETIN FISIKA 19, nr 1 (1.05.2018): 16. http://dx.doi.org/10.24843/bf.2018.v19.i01.p04.

Pełny tekst źródła

Streszczenie:

It has been created a program to recognize human voice by using artificial neural network (ANN). The ANN method used is Hebb. Hebb was chosen because it is the simplest ANN so the training and testing process is faster than other methods. Designing the program is started by designing Hebb’s architecture and design of GUI (Graphical User Interface) using Matlab R2009a. The design of Hebb's architecture consists of 4500 inputs and 3 outputs. The GUI design of the program consists of three main sections: recording panels to record sample sounds, training panels to determine the weighted value and bias of the training results according to the Hebb training algorithm, and the testing panel to test the test sounds according to the Hebb testing algorithm. After program design, proceed with the testing of the program. Testing of the program starts with the sound recording of samples from 8 different people using the record panel. Each person has 1 voice sample for training data. Then proceed with the Hebb training process using the training panel, weight and bias value displayed on the training panel. After the weight and bias values ??are obtained, proceed with the Hebb testing process using 16 test sound data consisting of 8 sound data equal to training data and 8 noise data. From the testing program process obtained a result of 100% for the level of recognition of the same voice data with training data and for noise data has a recognition rate of 87.5%.

Style APA, Harvard, Vancouver, ISO itp.

50

Thar, Min Htet, i Dong Myung Lee. "Sound Sources Recognition System Based on Convolutional Neural Network Using a New Dataset in Noisy Environment". Journal of Computational and Theoretical Nanoscience 18, nr 5 (1.05.2021): 1416–22. http://dx.doi.org/10.1166/jctn.2021.9611.

Pełny tekst źródła

Streszczenie:

A sound source recognition system based on a convolutional neural network (CNN) using a new dataset in a noisy environment was proposed and its performance was analyzed in this paper. The deep learning model in the system consists of a convolutional layer with max-pooling and a fully connected layer based on CNN, and classifies short audio clips of surrounding sounds. The performance of the proposed system was produced by measuring with the confusion matrix (CM) and the sound source recognition accuracy (SSRA). As a result of comparing the average SSRA of the proposed system applying the new sound dataset reflecting the background noise condition and the existing system applying the noiseless dataset, it was measured as 72–76% and 40–55%, respectively. Finally, it can be seen that the case of applying the new sound source dataset was superior to the case of applying the noiseless dataset by about 21–32% on average.

Style APA, Harvard, Vancouver, ISO itp.

Artykuły w czasopismach na temat „Sound recognition”

Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych