This thesis deals with description of human hearing, audio and speech codecs, description of objective measure of quality and practical comparison of codecs. Chapter about audio codecs consists of description of lossless codec FLAC and lossy codecs MP3 and Ogg Vorbis. In chapter about speech codecs is description of linear predictive coding and G.729 and OPUS codecs. Evaluation of quality consists of description of segmental signal-to- noise ratio and perceptual evaluation of quality – WSS and PESQ. Last chapter deals with description od practical part of this thesis, that is comparison of memory and time consumption of audio codecs and perceptual evaluation of speech codecs quality.

La llegada del sonido 3D está imponiendo cambios en varias etapas del flujo de trabajo, desde los sistemas de captación hasta las metodologías de postproducción y las configuraciones de altavoces. Esta tesis trata varios aspectos relacionados con el audio 3D: en la parte de captación, presentamos un estudio sobre las características de los micrófonos tetraédricos y una solución para obtener las componentes Ambisonics del segundo orden usando un pequeño número de transductores del primer orden; en la parte de producción, se presenta una aplicación para la mezcla automatizada de eventos deportivos, para reducir la complexidad del multicanal en tiempo real; para la restitución del audio independiente del sistema de altavoces, en el que los niveles de salida a los altavoces son una incógnita hasta la decodificación, se propone un detector de clipping independiente del layout. Finalmente, se presentan test psico-acústicos para validar aspectos perceptivos relacionados con el audio 3D. / The advent of 3D audio is dictating changes in several stages of the audio work-flow, from recording systems and microphone configurations, to post-production methodologies and loudspeaker configurations. This thesis tackles aspects related to 3D audio arising in the various stages of production. In the recording part, we present a study on the accuracy of tetrahedral microphones and a solution for obtaining second-order Ambisonics responses from first-order transducers using a small number of sensors; in the production stage, we introduce an application for automated assisted mixing of sport events, to reduce the complexity of managing multiple audio channels in real time; a clipping detector is proposed for the rendering of layout-independent audio content to generic playback systems, where the signal levels sent to the speakers are unknown until the decoding stage; finally, psychoacoustic experiments are presented for the validation of perceptual and aesthetic aspects related to 3D audio.

The master's thesis deals with the restoration of audio signals that have been damaged by clipping. Used methods are based on sparse representations of signals. The introduction of the thesis explains the issue of clipping and mentions the list of already existing methods that solve declipping, which are followed by the thesis. In the next chapter, the necessary theory of sparse representations and the proximal algorithms is described, including specific representatives from the category of convex optimization problems. The thesis contains declipping algorithm implemented in Matlab software environment. Chosen method for solving the task uses the Condat algorithm or Generic proximal algorithm for convex optimization and solves minimization of sum of three convex functions. The result of the thesis is five versions of algorithm and three of them have implemented psychoacoustic model for results improvement. For each version has been found optimal setting of parameters. The restoration quality results are evaluated using objective measurements like SDR and PEMO-Q and also using subjective listening test.

The point of this thesis was to perform listening tests. Appropriate methods of performance were selected for these tests, tests were carried out and the data were analyzed using statistical analysis. Then was compiled the resulting interval scale from results of the first test and in the second listening test were determined average values SNR for background noises.

The dissertation thesis focuses on objective assessment and reduction of disturbing background noise in a musical signal. In this work, a new algorithm for the assessment of background noise audibility is proposed. The listening tests performed show that this new algorithm better predicts the background noise audibility than the existing algorithms do. An advantage of this new algorithm is the fact that it can be used even in the case of a general audio signal and not only musical signal, i.e. in the case when the audibility of one sound on the background of another sound is assessed. The existing algorithms often fail in this case. The next part of the dissertation thesis deals with an adaptive segmentation scheme for the segmentation of long-term musical signals into short segments of different lengths. A new adaptive segmentation scheme is then introduced here. It has been shown that this new adaptive segmentation scheme significantly improves the subjectively perceived quality of the musical signal from the output of noise reduction systems which use this new adaptive segmentation scheme. The quality improvement is better than that achieved by other segmentation schemes tested.

<p>This thesis aims to investigate how one fundamental component of the inner-ear (cochlear) response to all sounds, the temporal fine structure (TFS), is used by the auditory system in everyday hearing. Although it is well known that neurons in the cochlea encode the TFS through exquisite phase locking, how this initial/peripheral temporal code contributes to everyday hearing and how its degradation contributes to perceptual deficits are foundational questions in auditory neuroscience and clinical audiology that remain unresolved despite extensive prior research. This is largely because the conventional approach to studying the role of TFS involves performing perceptual experiments with acoustic manipulations of stimuli (such as sub-band vocoding), rather than direct physiological or behavioral measurements of TFS coding, and hence is intrinsically limited. The present thesis addresses these gaps in three parts: 1) developing assays that can quantify TFS coding at the individual level 2) comparing individual differences in TFS coding to differences in speech-in-noise perception across a range of real-world listening conditions, and 3) developing deep neural network (DNN) models of speech separation/enhancement to complement the individual-difference approach. By comparing behavioral and electroencephalogram (EEG)-based measures, Part 1 of this work identified a robust test battery that measures TFS processing in individual humans. Using this battery, Part 2 subdivided a large sample of listeners (N=200) into groups with “good” and “poor” TFS sensitivity. A comparison of speech-in-noise scores under a range of listening conditions between the groups revealed that good TFS coding reduces the negative impact of reverberation on speech intelligibility, and leads to reduced reaction times suggesting lessened listening effort. These results raise the possibility that cochlear implant (CI) sound coding strategies could be improved by attempting to provide usable TFS information, and that these individualized TFS assays can also help predict listening outcomes in reverberant, real-world listening environments. Finally, the DNN models (Part 3) introduced significant improvements in speech quality and intelligibility, as evidenced by all acoustic evaluation metrics and test results from CI listeners (N=8). These models can be incorporated as “front-end” noise-reduction algorithms in hearing assistive devices, as well as complement other approaches by serving as a research tool to help generate and rapidly sub-select the most viable hypotheses about the role of TFS coding in complex listening scenarios.</p>

Objectif: Cette thèse avait pour objectif principal la mise en oeuvre et la validation de la faisabilité, chez l'humain, du paradigme de modulation du réflexe acoustique de sursaut par un court silence (GPIAS) afin de l'utiliser comme mesure objective de l'acouphène. Pour ce faire, trois expériences ont été réalisées. L'expérience 1 avait pour objectif de valider l'inhibition du réflexe de sursaut par un court silence chez des participants humains normo-entendants (sans acouphène) lors de la présentation d'un bruit de fond centré en hautes et en basses fréquences afin de déterminer les paramètres optimaux du paradigme. L'expérience 2 avait pour objectif de valider la précision et la fidélité d'une méthode de caractérisation psychoacoustique de l'acouphène (appariement en intensité et en fréquence). Finalement, l'expérience 3 avait pour objectif d'appliquer le paradigme d'objectivation de l'acouphène par le réflexe de sursaut à des participants atteints d'acouphènes chroniques en utilisant les techniques développées lors des expériences 1 et 2. Méthodologie : L'expérience 1 incluait 157 participants testés dans l'une des conditions de durée du court silence (5, 25, 50, 100, 200 ms) et dans l'un des deux paradigmes (court silence à l'intérieur du bruit de fond ou suivant celui-ci) à l'aide de bruits de fond en hautes et en basses fréquences. L'expérience 2 incluait deux groupes de participants avec acouphène, l'un musicien (n=16) et l'autre sans expérience musicale (n=16) ainsi qu'un groupe de simulateur sans acouphène (n=18). Ils tous ont été évalués sur leur capacité d'appariement en fréquence et en intensité de leur acouphène. Les mesures ont été reprises chez un sous-groupe de participants plusieurs semaines plus tard. L'expérience 3 incluait 15 participants avec acouphène et 17 contrôles évalués à l'aide du paradigme d'inhibition du réflexe de sursaut à l'aide d'un court silence (GPIAS). Les paramètres psychoacoustiques de l'acouphène ont également été mesurés. Toutes les mesures ont été reprises plusieurs mois plus tard chez un sous-groupe de participants. Résultats : Expérience 1 : le paradigme d'inhibition du réflexe acoustique de sursaut par un court silence est applicable chez l'humain normo-entendant. Expérience 2 : les mesures psychoacoustiques informatisées de l'acouphène incluant l'appariement en fréquence et en intensité sont des mesures précises et fidèles du percept de l'acouphène. Expérience 3 : un déficit d'inhibition au paradigme du GPIAS a été retrouvé chez le groupe de participants avec acouphène pour les bruits de fond en hautes et en basses fréquences au test et au retest. Les mesures d'appariement en fréquence ont révélé un acouphène dont la fréquence prédominante était d'environ 16 000 Hz chez la plupart des participants. Discussion : Il est possible d'appliquer le paradigme d'inhibition du réflexe acoustique de sursaut par un court silence à des participants humains atteints d'acouphène, tel qu'il est utilisé en recherche animale pour « objectiver » la présence d'acouphène. Toutefois, le déficit d'inhibition mesuré n'est pas spécifique à la fréquence de l'acouphène lorsque validé à partir des données d'appariement psychoacoustique. Nos résultats soulèvent des questions quant à l'interprétation originale du paradigme pour détecter la présence d'un acouphène chez les animaux. / Objective: The main objective of this thesis was the implementation and validation of applying the gap prepulse inhibition of the acoustic startle reflex (GPIAS) paradigm in humans, in order to objectively measure tinnitus. To do this, three experiments were carried out. Experiment 1 was designed to validate the inhibition of the acoustic startle reflex by using a short gap within high and low frequency narrowband noise in normal hearing humans (without tinnitus) to determine the optimal paradigm parameters. Experiment 2 was designed to validate the accuracy and the test-retest fidelity of a tinnitus psychoacoustic characterization method (intensity and frequency matching). Finally, Experiment 3 applied the GPIAS paradigm to participants with chronic tinnitus using the techniques developed in experiments 1 and 2. Methods: Experiment 1 included 157 participants tested with only one gap duration (5, 25, 50, 100, 200 ms) and with one of the two paradigms (gap imbedded in the background noise or following it) including high and low frequencies background noise. Experiment 2 included two groups of participants with tinnitus, one group consisting of musicians (n=16) and one group without musical experience (n=16). A third group consisted of adults who were instructed to simulate having tinnitus (n = 18). Tinnitus pitch and intensity matching abilities were assessed for all participants. A subgroup of participants was retested several weeks later. Experiment 3 included 15 participants with tinnitus and 17 controls assessed with the GPIAS. The psychoacoustic parameters of tinnitus were also measured. A subgroup of participants was retested several weeks later. Results: Experiment 1: the GPIAS is applicable in humans with normal hearing. Experiment 2: psychoacoustic measurements of tinnitus frequency and intensity using a computerized matching procedure produced precise and accurate measurements of the tinnitus percept. Experiment 3: an inhibition deficit was found using the GPIAS paradigm in the tinnitus group for background noise of high and low frequency compared to the control group, at test and retest. The frequency matching measurements revealed a 16,000 Hz tinnitus predominant frequency for most tinnitus participants. Discussion: It is possible to apply the gap prepulse inhibition of the startle reflex paradigm on human participants with tinnitus, as used in animal research to "objectify" the presence of tinnitus. However, the inhibition deficit found in the tinnitus group was not specific to their tinnitus frequency. This was validated by psychoacoustic tinnitus pitch matching. Our results question the original interpretation of the GPIAS paradigm for objectifying the presence of tinnitus.

Στην παρούσα εργασία επιχειρείται η εφαρμογή αλγορίθμων αποθορυβοποίησης σε σήματα μουσικής και η εξαγωγή συμπερασμάτων σχετικά με την απόδοση αυτών ανά μουσικό είδος. Η κύρια επιδίωξη είναι να αποσαφηνιστούν τα βασικά προβλήματα της ενίσχυσης ήχων και να παρουσιαστούν οι διάφοροι αλγόριθμοι που έχουν αναπτυχθεί για την επίλυση των προβλημάτων αυτών. Αρχικά γίνεται μία σύντομη εισαγωγή στις βασικές έννοιες πάνω στις οποίες δομείται η τεχνολογία ενίσχυσης ομιλίας. Στην συνέχεια εξετάζονται και αναλύονται αντιπροσωπευτικοί αλγόριθμοι από κάθε κατηγορία τεχνικών αποθορυβοποίησης, την κατηγορία φασματικής αφαίρεσης, την κατηγορία στατιστικών μοντέλων και αυτήν του υποχώρου. Για να μπορέσουμε να αξιολογήσουμε την απόδοση των παραπάνω αλγορίθμων χρησιμοποιούμε αντικειμενικές μετρήσεις ποιότητας, τα αποτελέσματα των οποίων μας δίνουν την δυνατότητα να συγκρίνουμε την απόδοση του κάθε αλγορίθμου. Με την χρήση τεσσάρων διαφορετικών μεθόδων αντικειμενικών μετρήσεων διεξάγουμε τα πειράματα εξάγοντας μια σειρά ενδεικτικών τιμών που μας δίνουν την ευχέρεια να συγκρίνουμε είτε τυχόν διαφοροποιήσεις στην απόδοση των αλγορίθμων της ίδιας κατηγορίας είτε διαφοροποιήσεις στο σύνολο των αλγορίθμων. Από την σύγκριση αυτή γίνεται εξαγωγή χρήσιμων συμπερασμάτων σχετικά με τον προσδιορισμό των παραμέτρων κάθε αλγορίθμου αλλά και με την καταλληλότητα του κάθε αλγορίθμου για συγκεκριμένες συνθήκες θορύβου και για συγκεκριμένο μουσικό είδος. / This thesis attempts to apply Noise Reduction algorithms to signals of music and draw conclusions concerning the performance of each algorithm for every musical genre. The main aims are to clarify the basic problems of sound enhancement and present the various algorithms developed for solving these problems. After a brief introduction to basic concepts on sound enhancement we examine and analyze various algorithms that have been proposed at times in the literature for speech enhancement. These algorithms can be divided into three main classes: spectral subtractive algorithms, statistical-model-based algorithms and subspace algorithms. In order to evaluate the performance of the above algorithms we use objective measures of quality, the results of which give us the opportunity to compare the performance of each algorithm. By using four different methods of objective measures to conduct the experiments we draw a set of values that facilitate us to make within-class algorithm comparisons and across-class algorithm comparisons. From these comparisons we can draw conclusions on the determination of parameters for each algorithm and the appropriateness of algorithms for specific noise conditions and music genre.