Dissertationen zum Thema „Stereo audio“

Thesis (B.S.)--California Polytechnic State University, 2009.
Project advisor: Dennis Derickson. Title from PDF title page; viewed on Feb. 4, 2010. Includes bibliographical references. Also available on microfiche.

This text analyzes characteristics of audio power amplifiers in class D. The emphasis is placed on more detailed analysis of modulators, drivers, connection topology of power transistors. In the next section of text are analyzed available integrated circuits of power amplifiers in class D which are manufactured by world producers. The last part describes design of all parts of amplifier in class D with discrete components and also of power supplies. According to the plans, the individual parts are made. All parts are tested by measurements and results are evaluated.

Depuis une dizaine d’années, des techniques de codage joint, exploitant les relations et les redondances entre canaux audios, ont été développées afin de réduire davantage la quantité d’information nécessaire à la représentation des signaux multicanaux. Dans cette thèse, nous étudions plus particulièrement le codage des signaux audio stéréo en l’absence d’informations à priori sur la nature des sources en présences, leur nombre et la manière dont elles sont spatialisées. Cette situation correspond à l’immense majorité des enregistrements commerciaux dans l’industrie de la musique et du multimédia de manière générale. Nous étudions des approches paramétrique et signal de la problématique de codage de ces sources, où les deux sont souvent mêlées. Dans ce contexte, trois types d’approches sont utilisés. L’approche paramétrique spatiale consiste à réduire le nombre de canaux audio de la source à coder et à recréer le nombre de canaux d’origine à partir des canaux réduits et de paramètres spatiaux, extraits des canaux d’origine. L’approche signal conserve le nombre de canaux d’origine, mais encode des canaux construits à partir de ces derniers et présentant moins de redondances. Enfin, l’approche mixte introduite dans MPEG USAC utilise un signal audio et un signal résiduel, issu d’une prédiction, et dont les paramètres sont codés conjointement. Dans cette thèse, nous analysons tout d’abord les caractéristiques d’un signal stéréo issu d’un enregistrement commercial et les techniques de production associées. Cette étude nous mène à une réflexion sur les rapports entre les modèles paramétriques d’émetteur, obtenus en analysant les techniques de production des enregistrements commerciaux, et les modèles de récepteur qui sont au coeur du codage spatial paramétrique. A partir de cette mise en perspective nous présentons et étudions les trois approches évoquées plus haut. Pour l’approche purement paramétrique, nous montrons l’impossibilité d’arriver à la transparence pour la majorité des sources audios, nous menons une réflexion sur les représentations paramétriques et proposons des techniques afin de réduire le débit de leurs paramètres et d’améliorer la qualité audio. Ces améliorations passent par une meilleur segmentation du signal audio, basée sur les transitoires, sur des caractéristiques perceptives de certains indices spatiaux et sur une meilleur estimation des indices spatiaux. L’approche mixte étant récemment standardisée dans MPEG USAC, nous l’étudions en détail, puis nous proposons une nouvelle technique de codage qui exploite au mieux l’allocation du résidu aux bandes fréquentielles, lorsque celui-ci n’est pas utilisé sur l’ensemble de la bande passante du signal. Enfin, nous concluons en évoquant l’avenir du codage audio spatial généraliste et mettons l’accent sur l’importance de développer des techniques de classification et de segmentation audio pour optimiser le rapport qualité/débit
During the last ten years, technics for joint coding exploiting relations and redundancies between channels have been developped in order to further reduce the amount of information needed to represent multichannel audio signals.In this document, we focus on the coding of stereo audio signals where prior informations on the nature of sources in presence, their number or the manner they are spatialized is unknown. Such signals are actually the most representative in commercial records of music industry and in multimedia entertainment in general. To address the coding problematic of these signals, we study parametric and signal approaches, where both of them are often mixed.In this context, three types of approaches are used. The spatial parametric approach reduce the number of audio channels of the signal to encode and recreate the original number of channels from reduced channels and spatial parameters extracted from original channels. The signal approach keep the original number of channels, but encode mono signals, built from the combination of the original ones and containing less redundancies. Finally, the hybrid approach introduced in the MPEG USAC standard keep the two channels of a stereo signal, but one is a mono downmix and the other is a residual signal, resulting from a prediction on the downmix, where prediction parameters are encoded as side information.In this document, we first analyse the characteristics of a stereo audio signal coming from a commercial recording and the associated production techniques. This study lead us to consider the relations between the emitter parametric models, elaborated from our analysis of commercial recording production techniques, and the receiver models which are the basis of spatial parametric coding. In the light of these considerations, we present and study the three approaches mentioned earlier. For the parametric approach, we show that transparency cannot be achieved for most of the stereo audio signals, we have a reflection on parametric representations and we propose techniques to improve the audio quality and further reduce the bitrate of their parameters. These improvements are obtained by applying a better segmentation on the signal, based on the significant transient, by exploiting perceptive characteristics of some spatial cues and by adapting the estimation of spatial cues. As the hybrid approach has been recently standardized in MPEG USAC, we propose a full review of it, then we develop a new coding technique to optimize the allocation of the residual bands when the residual is not used on the whole bandwidth of the signal to encode. In the conclusion, we discuss about the future of the general spatial audio coding and we show the importance of developping new technics of segmentation and classification for audio signals to further adapt the coding to the content of the signal

Recent advancements in audio technology for computer games has made possible for implementations with binaural audio. Compared to regular stereo sound, binaural audio offers possibilities for a player to experience spatial sound, including sounds along the vertical plane, using their own headphones. A computer game prototype called “Crystal Gatherer” was created for this study to explore the possibilities of binaural audio imple- mentation regarding localization and perception of objects that make sound in a 3D game. The game featured two similar game levels, with the difference that one used binaural sound, and the other stereo sound. The levels consisted of a dark space that the player could navigate freely with the objective to find objects that make sound, called “crystals”, as fast as they could. An experiment was conducted with 14 test sub- jects that played the game, qualitative and quantitative data was collected, including the time the players took to complete the game levels, respectively, and answers about how they experienced the levels. A majority of test subjects reported that they per- ceived a difference between the levels. No significant difference was found between the levels in terms of efficacy of finding the objects that made sound. Some test subjects stated that they found localization was better in the binaural level of the game, others found the stereo level to be better in this respect. The study shows that there can exist possibilities for binaural audio to change the perception of audio in computer games.

Résumé : Afin de répondre aux besoins de communication et de divertissement, il ne fait aucun doute que la parole et l’audio doivent être encodés sous forme numérique. En qualité CD, cela nécessite un débit numérique de 1411.2 kb/s pour un signal stéréo-phonique. Une telle quantité de données devient rapidement prohibitive pour le stockage de longues durées d’audio ou pour la transmission sur certains réseaux, particulièrement en temps réel (d’où l’adhésion universelle au format MP3). De plus, ces dernières années, la quantité de productions musicales et cinématographiques disponibles en cinq canaux et plus ne cesse d’augmenter. Afin de maintenir le débit numérique à un niveau acceptable pour une application donnée, il est donc naturel pour un codeur audio à bas débit d’exploiter la redondance entre les canaux et la psychoacoustique binaurale. Le codage perceptuel et plus particulièrement le codage paramétrique permet d’atteindre des débits manifestement inférieurs en exploitant les limites de l’audition humaine (étudiées en psychoacoustique). Cette recherche se concentre donc sur le codage paramétrique à bas débit de plus d’un canal audio. // Abstract : In order to fulfill our communications and entertainment needs, there is no doubt that speech and audio must be encoded in digital format. In"CD" quality, this requires a bit-rate of 1411.2 kb/s for a stereo signal. Such a large amount of data quickly becomes prohibitive for long-term storage of audio or for transmitting on some networks, especially in real-time (leading to a universal adhesion to the MP3 format). Moreover, throughout the course of these last years, the number of musical and cinematographic productions available in five channels or more continually increased.In order to maintain an acceptable bit-rate for any given application, it is obvious that a low bit-rate audio coder must exploit the redundancies between audio channels and binaural psychoacoustics. Perceptual audio coding, and more specifically parametric audio coding, offers the possibility of achieving much lower bit-rates by taking into account the limits of human hearing (psychoacoustics). Therefore, this research concentrates on parametric audio coding of more than one audio channel.

To light up the world of technology, where wireless communication has bloomed to a great extend which requires a lot of data to be transmitted and received every fraction of the second a new era is coming. Electro-magnetic waves i.e., radio waves are the main way to transmit wireless data but certain limitations are there because radio waves can only support less bandwidth because of compact spectrum availability and intrusions. Visible Light Communication (VLC) has come to take way those issues. The new technology Li-Fi which stands for Light-Fidelity is a new kind of wireless communication system which uses light waves as a medium instead of radio frequency electromagnetic waves. This pro-ject presents an eco-friendly data communication system through visible light which consists of LEDs that transmit audio signals and sensor data to the receiver. A connection protection mechanism that co-operates with wireless network and visible light communication to achieve relia-bility and performance overcoming the drawbacks from the pre-existing system is proposed here.

This dissertation presents an optical approach for reproducing stereo audio from the stereo disc phonograph records (LPs). Since the late nineteenth century, as one of the most influential recording technologies, the phonograph recording has enjoyed its popularity and produced numerous cylinders and discs that carry speeches, music, and all kinds of audio cultural heritage. The preservation of phonograph sound recordings is thus of world-wide concern. This research provides an alternative approach to digitizing the stereo disc phonograph records, potentially for long-term preservation, by optically acquiring the 3D disc record surface profile and extracting the audio signals from the record surface profile images by using software algorithms. The dissertation discusses the workflow of optically reproducing stereo audio from the stereo disc phonograph records by using the white-light interferometry technique. This workflow includes the acquisition of the 3D disc record surface profile by using a commercial white-light interferometry microscope, the extraction of the record groove undulations, which encodes the stereo audio information, by using our custom image processing algorithms, and finally the reproduction of the stereo audio signal from the groove undulations through signal processing. The workflow is evaluated with a test stereo record containing standard sinusoid signals and a musical record. The quality of the optically-reproduced audio is quantitatively evaluated and compared with that of the audio digitized by a turntable. The dissertation contains three main parts. The first include an introduction to the general background of the optical audio reproduction for the stereo disc phonograph records and the review of the phonograph recording technology, the previous efforts in optically reproducing audio from the cylinder and disc phonograph records, and the relevant optical techniques including the white-light interferometry. The second part focuses on our complete workflow for optically reproducing the stereo audio from the stereo disc phonograph records. This is followed by the evaluation of our workflow and the output audio quality. The dissertation concludes by introducing the challenges and the possible directions in the future development of our optical audio reproduction workflow.
Cette thèse présente une nouvelle approche de reproduction optique d'enregistrements phonographiques stéréo. L'enregistrement phonographique s'est imposé, vers la fin du XIXème siècle, comme la technologie d'enregistrement de référence partout dans le monde. Il existe donc une pléthore de cylindres et autres disques où ont été gravés discours, morceaux de musique, et autres artefacts culturel sonores. La préservation de ces enregistrements sonores phonographiques est donc une préoccupation mondiale. Le présent travail de recherche propose une approche alternative de numérisation des enregistrements phonographiques stéréo en vue de leur éventuelle préservation. En effet, à partir de l'acquisition optique du profil (en trois dimensions) de la surface d'enregistrement du disque, les signaux audio peuvent être reconstruits grâce à nos algorithmes d'analyse d'images. Cette thèse examine les étapes de la reproduction optique audio stéréo à partir d'enregistrements phonographiques sur disques stéréo en utilisant l'interférométrie en lumière blanche. Ces étapes comportent: l'acquisition du profil de la surface d'enregistrement d'un disque 3D en utilisant un microscope commercial interférométrique en lumière blanche ; l'extraction des ondulations du sillon, qui encode l'information audio stéréo en utilisant nos algorithmes de traitement d'images ; et finalement, la reproduction du signal audio stéréo depuis les ondulations du sillon par des techniques de traitement du signal. Le processus complet est évalué sur un enregistrement stéréo test comprenant des signaux sinusoïdaux et un enregistrement musical. La qualité de l'audio reproduit par voie optique est évaluée de façon quantitative et comparée avec celle de l'audio numérisé de manière « traditionnelle », à l'aide d'une platine. Cette thèse s'articule en trois parties. La première comporte une introduction des principes nécessaires à la reproduction d'enregistrements phonographiques stéréo par voie optique. Plus précisément, les principes de la technologie d'enregistrement phonographique sont passés en revue ; l'état de l'art des efforts de reproduction optique des enregistrements phonographiques sur disques et cylindres est présenté ; et enfin, les techniques optiques pertinentes incluant l'interférométrie en lumière blanche sont décrites. La deuxième partie livre une présentation détaillée du processus de reproduction optique que nous avons développé. Dans la troisième partie, l'évaluation quantitative de la qualité de la restitution du signal audio obtenue par notre procédé est aussi décrite. La thèse se conclue sur un bilan des défis et des directions possibles dans le futur développement de notre approche de reproduction des signaux audio par voie optique.

This thesis analyses if the change of auditory feedback can improve the effectiveness of performance in the interaction with a non-visual system, or with a system used by individuals with visual impairment. Two prototypes were developed, one with binaural audio and the other with stereo audio. The interaction was evaluated in an experiment where 22 participants, divided into two groups, performed a number of interaction tasks. A post-interview were conducted together with the experiment. The result of the experiment displayed that there were no great difference between binaural audio and stereo regarding the speed and accuracy of the interaction. The post-interviews displayed interesting differences in the way participants visualized the virtual environment that affected the interaction. This opened up interesting questions for future studies.

This thesis presents a stereo coding architecture for the ITU-T G.719 fullband mono codec. G.719 is suitable for teleconferencing applications with a competitive audio quality for speech and audio signals that are encoded at 32, 48 and 64 kbps. The proposed stereo architecture comprises parametric stereo coding where the spatial properties of the stereo channels are modeled with the use of parameters, which are encoded and transmitted to the decoder together with an encoded downmix of the stereo channels. The stereo architecture has been implemented in MATLAB with an external mono coding using a floating point ANSI-C implementation of the ITU-T G.719 codec. Two parametric stereo models have been implemented in a framework operating in the complex-valued Modified Discrete Fourier Transform (MDFT) domain. The first model is based on the inter-channel cues that represent level differences, time differences and coherences between the stereo channels. The cues approximate the corresponding interaural cues that characterize our localization of sound in space. The second model is based on the Karhunen-Loève Transform (KLT) with the associated rotation angles, the inter-channel time differences and the residual scaling parameters. An improved MDFT domain extraction of the inter-channel time difference between the stereo channels has been used for both stereo models. The extracted stereo parameters have been non-uniformly quantized based on the spatial accuracy and the frequency dependency of the human auditory system. The data rate of the stereo parameters has been estimated for each model to around 4 kbps. As a result G.719 has been used as a core codec at 44 and 60 kbps in order to subjectively evaluate the performance of the fullband stereo codec at 48 and 64 kbps. In the comparison with G.719 dual mono coding, i.e. independent mono coding of the stereo channels, the evaluation showed a higher performance of the proposed stereo models for complex clean and reverberant speech signals. However, no consistent gain of the parametric stereo coding was revealed for noisy speech, mixed content and music signals. In addition, the first stereo model showed consistently a slightly higher performance than the second model in the subjective evaluation but with no significant difference. The results revealed a high potential for parametric stereo coding using the ITU-T G.719 codec. In comparison to the existing stereo codecs 3GPP AMR-WB+ and 3GPP eAAC+ the average performance was better at the equal bitrate of 48 kbps.

Cette thèse développe de nouvelles techniques de codage de parole et audio scalables. Tout d’abord, une première méthode de codage par transformée des signaux de parole et audio scalable est présentée. Cette méthode est construite sur le principe de codage par plan de bits, qui est une technique efficace pour atteindre un codage progressif scalable. Cette technique décompose une séquence entière à coder en une succession de plans de bits, des bits les plus significatifs (MSB) aux bits les moins significatifs (LSB). Ces plans de bits dans le train binaire généré peuvent être arbitrairement tronqués lorsque certaines contraintes sont appliquées. Chaque plan de bits est ensuite converti en une séquence quinaire (+, -, 0, 1, EoP), où le symbole “EoP” (End of Plane) indique la fin du plan courant. Un codage arithmétique contextuel est finalement appliqué sur cette séquence quinaire. Pour exploiter la corrélation entre les plans de bits successifs, les plans ne sont pas codés de façon séquentielle (du premier bit au dernier bit), mais en deux passes, en fonction des plans précédemment codés. En plus des techniques scalables dans le codage mono, les techniques scalables dans le codage audio multicanal ont été également développées. Cette thèse propose deux techniques de downmix stéréo en mono dans le domaine fréquentiel. Ces deux techniques de downmix ont plusieurs avantages: conserver l’énergie des composantes spectrales et éviter de mettre le canal left (L) ou right (R) comme référence de phase. En particulier, la deuxième technique de downmix permet de plus d’éviter la dégradation de qualité du signal mono dans le cas où les deux canaux stéréo sont en quasi opposition de phase (voire même en opposition de phase dans le cas extrême). Construits sur ces deux techniques de downmix, deux modèles d’analyse-synthèse stéréo paramétriques sont décrits. Dans ces modèles, les paramètres stéréo par sous-bande se composent soit de différence intercanale d’intensité, soit de différence intercanale de temps, soit de différence intercanale de phase entre le signal mono et un des deux signaux stéréo (L ou R). Ces deux modèles de codage stéréo paramétrique sont appliqués à l’extension stéréo de l’UIT-T G. 722 à deux modes: 56+8 et 64+16 kbit/s avec une longueur de trame de 5 ms

The identification of the melody from a music recording is a relatively easy task for humans, but very challenging for computational systems. This task is known as "audio melody extraction", more formally defined as the automatic estimation of the pitch sequence of the melody directly from the audio signal of a polyphonic music recording. This thesis investigates the benefits of exploiting knowledge automatically derived from data for audio melody extraction, by combining digital signal processing and machine learning methods. We extend the scope of melody extraction research by working with a varied dataset and multiple definitions of melody. We first present an overview of the state of the art, and perform an evaluation focused on a novel symphonic music dataset. We then propose melody extraction methods based on a source-filter model and pitch contour characterisation and evaluate them on a wide range of music genres. Finally, we explore novel timbre, tonal and spatial features for contour characterisation, and propose a method for estimating multiple melodic lines. The combination of supervised and unsupervised approaches leads to advancements on melody extraction and shows a promising path for future research and applications.
La identificación de la melodía en una grabación musical es una tarea relativamente fácil para seres humanos, pero muy difícil para sistemas computacionales. Esta tarea se conoce como "extracción de melodía", más formalmente definida como la estimación automática de la secuencia de alturas correspondientes a la melodía de una grabación de música polifónica. Esta tesis investiga los beneficios de utilizar conocimiento derivado automáticamente de datos para extracción de melodía, combinando procesado digital de la señal y métodos de aprendizaje automático. Ampliamos el alcance de la investigación en este campo, al trabajar con un conjunto de datos variado y múltiples definiciones de melodía. En primer lugar presentamos un extenso análisis comparativo del estado de la cuestión y realizamos una evaluación en un contexto de música sinfónica. A continuación, proponemos métodos de extracción de melodía basados en modelos de fuente-filtro y la caracterización de contornos tonales, y los evaluamos en varios géneros musicales. Finalmente, investigamos la caracterización de contornos con información de timbre, tonalidad y posición espacial, y proponemos un método para la estimación de múltiples líneas melódicas. La combinación de enfoques supervisados y no supervisados lleva a mejoras en la extracción de melodía y muestra un camino prometedor para futuras investigaciones y aplicaciones.

Based on previous research on spatial attributes in foley and the concept that auditory immersion in first-person perspective computer games is enhanced by believable sound effects, this study explores if there is a connection between stereo foley and the believability of the first-person perspective, and regardless, if there is a preference to either mono or stereo foley. An interactive listening test was created in unreal engine 4, where 20 subjects, all considered gamers, played three levels that differed visually and in auditory content. In these levels, subjects auditioned two versions of avatar-related foley sounds. One version was mono, the other stereo. The test prompted the subjects to complete two tasks for each level, whereupon the foley version changed upon completion of the first task. The subjects then answered questions in between each level, regarding the foley version. They were asked to rate believability and choose a preference, as well as provide motivations for their choices. The quantitative data showed next no evidence that either mono or stereo was generally perceived as more believable or preferred. However, the qualitative data indicates that the majority of players tend to prefer and rate stereo foley as more believable in certain game environments. Furthermore, the data indicates that some subjects prefer a sensory replication of reality in foley. It is also shown that preference for stereo width vary between subjects and therefore argued that there cannot be a perfect standardized setting for stereo foley.

Komatsu Forrest AB have a demand for a media solution where the user can select between different input sources as well as output channels. The input sources are Radio, Bluetooth, AUX, two microphones and PC. The system shall also be able to mix sound from an ANC unit (Active Noise Control). Due to the demands from the company, the system must be able to be digitally controlled. The goal is to present a concept that offers the solution for these demands.To specify the needs from the user a dialog with employees with more knowledge about the user’s use have resulted in a table. From this a technical design has been created and resulted in a technical design requirement. With the design structure as a base, simulations have been done. After the structure has been verified by simulations a prototype with the basic functions have been designed and programmed and verified to clarify the function.Simulations and measurements have shown that the design works as desired. The result shows that the unit can meet the requirements set by the company in a user-friendly manner. The project has resulted in different solutions and these evaluated for pros and cons compared to the chosen solution.
Komatsu Forest AB behöver en multimedialösning för att uppfylla specifika behov exempelvis simultant användande av två mobiltelefoner och två mikrofoner. Enheten ska klara av att hantera ljud från flertalet ljudkällor samt två mikrofoner och aktiv bullerreducering. Systemet ska styras digitalt från till exempel en PC. Målet är att presentera ett koncept som erbjuder en lösning för dessa problem.Utformningen av enheten har gjorts genom att utvärdera användarens bruksområden tillsammans med den vision som legat till grund för projektet. Detta har genom samtal med anställda på företaget medfört en sammanställning över förarens användnings-områden. Utifrån denna sammanställning av användningsområdena har en teknisk skiss för enhetens uppbyggnad möjliggjorts. Efter att funktionen för skissen har verifierats med simuleringar har ett prototypkort för enhetens grundstomme konstrueras, programmerats samt verifierat konstruktionen.Simuleringar och mätningar verifierar att konstruktionen fungerar som önskat. Resultatet visar att enheten skulle uppfylla de uppsatta önskemålen på ett bra och användarvänligt sätt. Då flera lösningar har tagits fram under projektets gång diskuteras för och nackdelar med dessa samt motiveras varför den valda lösningen är bäst anpassad.

碩士
國立臺北科技大學
資訊工程系研究所
96
With the growing use of portable devices, the need for wireless connectivity on portable devices is also increasing. Due to the limitation of bandwidth and storage on portable devices, many low bit-rate audio compression methods have been proposed. The amendment of ISO standard MPEG-4 part 3 Advanced Audio Coding (AAC) published in 2001, includes two modules, Spectral Band Replication (SBR) and Parametric Stereo (PS), for enhancing the audio quality at low bit-rates. But according to some listening test reports, stereo music compressed with PS module may blur the spatial sound localization. Therefore, we want a tool to determine whether a piece of music may suffer this problem. In this thesis, we implement a spatial localization quality evaluation system. By giving original audio and compressed audio, the system is able to evaluate the spatial accuracy of the compressed audio. We can give an objective score of spatial quality for different compression methods with software.

碩士
國立中央大學
通訊工程研究所
98
The Parametric Stereo (PS) audio coding is an audio coding object of High Efficiency Advanced Audio Coding version 2 (HE-AAC v2) which was standardized by ISO/MPEG in 2004. Traditional audio codec, e.g. MP3 or AAC, utilize “Psycoaustic Model” and “Masking Effect” to achieve high compression efficiency. However, they mainly process the signal with single channel. Different from traditional audio codec, the PS audio coding incorporates the characteristics of two channels, to extract spatial parameters and to down-mixes stereo signals into a mono signal. The PS can save almost half data size which provides great help in storage and transmission. Nevertheless, the complexity of PS decoder is nearly twice larger than that of PS encoder, which causes a serious problem in implementing PS on portable devices. Therefore, this thesis proposes a modified PS coding scheme to reduce the complexity of decoder. The encoder extracts and transmits the additional residual parameters from the residual signal and the mono signal. On the contrary, the decoder reconstructs the residual signal by the mono signal and the transmitted residual parameters. In addition, we detect the existence of transient signal and measure the artifact of reconstructed residual signal. Finally, “Energy compesated algorithm” is proposed to reduce the artifact produced by the transient signal. The proposed scheme can improve the Objective Difference Grade (ODG) of audio quality measurement “EAQUAL” with 0.6 score. Combining with audio coder AAC, the modified PS coding scheme still maintains a good performance at low coding bitrates.

碩士
大同大學
資訊工程學系(所)
94
In this thesis, the method to extract the spatial information and single representing source of original sound field in stereo, and then synthesis them as demanded are proposed. The objective is to synthesize appropriate sound field corresponding to vary listening condition. The discussed situation is focused on multi-sources playing the same melody by the same music instrument aligned in line. Since each source plays the same melody, the same music scale would be played on the sector in time. Human perception is insensitive to the phase of audio. So we might assume that the magnitudes of spectrogram of each source is similar even their waveforms are different. Therefore, the signal received by microphone could be treated as the summation of one spectrogram with shifts in time and attenuation. It is similar to an image corrupted by a motion blur function. Thus, the concept of image-restoration may be applied to extract the spatial information and single representing source by which the property of time-frequency components of each original source could be represented. The sound field similar to original sound field can be synthesized using the extracted single representing source and the obtained spatial information. Also the spatial information can be modified to synthesize the different sound field for different playback conditions in pleasure. The simulation is performed to confirm the method in this thesis. And the result shows that the concept of image distortion/restoration process with sound spectrogram could be applied to the spatial information extraction and sound field resynthesis. There will be certain compression effects with applying the concept of decomposing and re-synthesizing in this thesis with multi-channel processing in the future.

碩士
國立清華大學
電機工程學系
87
During the last decades, storage and transmission of high quality digital audio are becoming more and more important in, for example, digital audio broadcasting (DAB) and high definition television (HDTV). However, the required storage of high quality digital audio is usually massive. As for the compact disc signals (sampling rate of 44.1 kHz and 16 bits/sample), the bitrate requirement is 44100 * 16 =705.6 kb/s per channel and 1.41 Mb/s for stereo audio, which is too high for most applications. Thus we must develop techniques to reduce the bitrate requirement. In this thesis, the perceptual audio coder is reviewed and a coder based on wavelet packet transform is proposed. The distinct points about the proposed coder include: (1) it uses the wavelet packet transform rather than conventional Fourier transform or discrete cosine transform to exploit the capability of wavelet in, for example, treating nonstationary signals. (2) It tries to remove the redundancies between left and right channels in stereo audio to further increase the compression rate. Several wavelets are simulated and compared for audio compression in our experiments. From the experiments, the symmetric wavelet has the best effect for the coder. Different types of audio signals are also experimented in this study. An FFT based perceptual audio coder is also implemented for performance comparison.

碩士
國立交通大學
資訊工程系
89
Two methods for allocating bits to each channel in 3 stereo coding mode, and parameter design of single loop bit allocation is presented in this thesis. Two methods are proposed based on the criterion that optimize the bit allocation result of each channel. One using combine partial bit allocation process to keep quality of two channels equal. Another estimating bit requirement of each channel by energy ratio of two channels. In stereo mode of MPEG - 1 Layer III, with parameter design of single loop bit allocation, better quality is achieved. In other two coding mode of joint stereo, with modifying of masking ability, 0.5 ~ 2db quality improvement is achieved.

碩士
國立臺灣大學
電機工程學研究所
101
Audio steganography is a technique that hiding messages into audio such that no one except the sender and intended recipient suspects the existence of the messages. In this paper we proposed a new method for stereo audio steganography, which employs some characteristics of human auditory system (HAS). Messages are embedded by inserting low-frequency and octave-equivalent pure tones into different channels. By comparing the frequency domain data of left channel and right channel, the hidden messages are detected. The experiment results demonstrate that comparing with the host audio, the quality of the message-hided audio generated by our method are nearly not decreased, thus malicious attackers will not perceive the hidden messages.

碩士
國立交通大學
資訊工程學系
84
The purpose of stereo audio signal coding is to reduce the required bit rate, while maintaining the signal quality after decoding. The ISO MPEG1 is the most widely used audio compression standard in many commercial applications. Among the vast commercial products, MPEG1 layers I and II coding processes are most widely adopted. MPEG1 layer II can achieve a transparent audio quality above 2x128 kbits/s by independent coding of the left and the right channels. With the use of joint stereo coding technique, such as intensity stereo coding in MPEG1, the decoded audio quality can be improved for the bit rate lower than 2x128 kbits/s. In this thesis, we analyze the data redundancy of stereo audio signals. The Karhunen-Loeve (KL) transform and inter-channel prediction methods are applied to exploit and analyze the data redundancy in the framework of MPEG1 layers I and II. On the KL transform, we propose two modified intensity stereo coding algorithms for MPEG1 layers I and II by KL transform to further improve the decoded stereo audio quality at bit rate below 2x128 kbits/s. Subjective and objective measurements show that the two algorithms have better stereo audio quality than the original MPEG1 method. On the inter-channel prediction, we consider the coding gains along with various parameters such as prediction order, prediction delay, time varying property, the required side information, etc.. The experiment results suggest the applying of inter- channel prediction in the low frequency bands, and transmission of the prediction coefficients once for longer frames to avoid the side information overhead.

碩士
國立交通大學
機械工程系所
94
This dissertation focuses on the 3D audio reproduction for two-channel stereo loudspeakers. To create spatial impression during audio reproduction, the head-related transfer function (HRTF) and the crosstalk cancellation system (CCS) are key elements in many audio spatializers. Two deconvolution approaches, the frequency-domain method and the time-domain method, are employed to design the required inverse filters. Different approaches to design audio spatializers with the HRTF, CCS, and their combination are compared. Issues in the implementation phase such as regularization, complex smoothing and structures of inverse filters are also addressed. In particular, two modified CCS approaches are proposed. In addition, upmix and downmix processing plays an important role in many audio applications, where the number of channels of either the audio content or the reproducing loudspeakers are limited. Various upmix and downmix methods are presented in this work. A comprehensive study is undertaken, by comparing a variety of the proposed approaches, to find guidelines and strategies for 3D audio technique to meet the ever increasing needs of multichannel stereophonic systems. All proposed methods were examined both objectively and subjectively, and had been proven to be effective in 3D audio reproduction.

碩士
國立臺灣科技大學
電子工程系
101
The digital pulse width modulation (DPWM) has been widely applied to power management IC, motor speed controller, LED driver, and Class-D amplifier. This thesis presents a dual-channel, high-resolution digital pulse width modulation (DPWM) applicable to Class-D audio amplifiers based on the specifications, operating frequency and resolution for CD audio. The DPWM incorporates ring oscillator along with counter for coarse duty adjustment, phase slection for medium duty adjustment and phase interpolation for fine duty tuning. The major advantages of the proposed structure are low cost, high resolution and monotonicity. The proposed DPWM chip is fabricated in a TSMC 0.18μm 1P6M standard CMOS process with a core size of merely 0.059 mm2. It is measured to function well within 263KHz ~ 418KHz operation frequency range. The resolution is 16-bit and the equivalent timing resolution is 43.25ps at 1.8V supply voltage. The power consumption is 39.6mW at 352.8 KHz and the integral nonlinearity is measured to be as small as -0.83~+0.84 LSB. The adjustable duty cycle ranges from 0 to 100%.

Tonmeisters tune the sound of music productions. Besides aspects like spectral bal- ance, loudness and dynamics, spaciousness plays an important role. Music of different genres tends towards different degrees of spaciousness due to generic aesthetic ideals and practical reasons. In this paper, we compare the degree of spaciousness as intended by the Tonmeister and perceived by the listener. 150 music excerpts from 5 different genres (electronica, classical, jazz, rock and ethno) are analyzed. The Tonmeister’s intention is derived from the literature and from analysis with a goniometer. The listeners perception is obtained from a listening test with 13 participants. The listening test revealed different adjectives for each genre relating to a spacious perception. We found that general rules as suggested in the literature are barely reflected in the goniometer results or the subjective impressions. Subjective impressions are largely contradictory.

The National Beef Quality Audit – 2011 assessed the current status of quality and consistency of fed steers and heifers. Beef carcasses (n = 9,802), representing approximately 10 percent of each production lot in 28 beef processing facilities, were selected randomly for the survey. Carcass evaluation for the cooler assessment of this study revealed these traits and frequencies: steer (63.5%), heifer (36.4%), cow (0.1%), and bullock (0.03%) sex classes; dark-cutters (3.2%); blood splash (0.3%); yellow fat (0.1%); calloused ribeye (0.05%); A (92.8%), B (6.0%), and C or greater (1.2%) overall maturities; native (88.3%), dairy-type (9.9%), and Bos indicus (1.8%) estimated breed types; and United States (97.7%), Mexico (1.8%), and Canada (0.5%) country of origin. Certified or marketing program frequencies were age and source verified (10.7%), ≤ A40 (10.0%), Certified Angus Beef (9.3%), top Choice (4.1%), natural (0.6%), and Non-Hormone Treated Cattle (0.5%), and there were no organic programs observed. Mean USDA YG traits were USDA YG (2.9), HCW (374.0 kg), AFT (1.3 cm), LM area (88.8 cm2), and KPH (2.3%); Frequencies of USDA YG distributions were YG 1 (12.4%), YG 2 (41.0%), YG 3 (36.3%), YG 4 (8.6%), and YG 5 (1.6%). Mean USDA QG traits were USDA QG (Select93), marbling score (Small40), overall maturity (A59), lean maturity (A54), skeletal maturity (A62). Frequencies of USDA QG distributions were Prime (2.1%), Choice (58.9%), Select (32.6%), and Standard or less (6.3%). Marbling score distribution was Slightly Abundant or greater (2.3%), Moderate (5.0%), Modest (17.3%), Small (39.7%), Slight (34.6%), and Traces or less (1.1%). Carcasses with QG of Select or greater and YG of 3 or numerically less represented 85.1% of the sample. This is the fifth benchmark study measuring targeted carcass characteristics, and information from this survey will continue to help drive progress in the beef industry. Results will be used in extension and educational programs as teaching tools to inform beef producers and industry professionals of the current state of the U.S. beef industry.