Contexte : Le démasquage binaural est un processus indispensable pour la compréhension en environnement bruyant. Ce mécanisme ferait intervenir la comparaison d’indices temporels et fréquentiels tout au long des voies nerveuses auditives. Cependant, il n’existe pas de réel consensus évoquant un traitement du démasquage à un niveau sous-cortical et/ou cortical. L’objet de cette étude est d’étudier ces indices temporels et fréquentiels du démasquage par le biais d’une étude perceptive, puis d’une étude électroencéphalographique (EEG). Matériels et méthodes : Une population normoentendante a été évaluée lors d’une étude perceptive visant à estimer l’importance du démasquage en fonction de 1) la largeur fréquentielle du bruit controlatéral (de 1 octave, 3 octaves ou à large bande), 2) la cohérence temporelle des bruits bilatéraux (corrélation égale à 0 ou 1) et 3) la fréquence des stimuli cibles (0,5, 1, 2 et 4 kHz). Puis, le démasquage a été évalué en EEG par l’étude 1) des latences précoces (<10 ms, PEA-P), 2) des latences tardives (<50 ms, PEA-T) et 3) de l’onde de discordance (PEA-MMN). Pour ces trois études EEG, l’influence de la cohérence temporelle des bruits bilatéraux a été explorée.Résultats : L’étude perceptive traduit un démasquage croissant lorsque la largeur fréquentielle du bruit controlatéral augmente. L’ajout du bruit controlatéral non corrélé (corrélation=0) se traduit par une amélioration de détection de 1,28 dB, quelle que soit la fréquence des stimuli cibles (antimasquage), alors que l’ajout d’un bruit controlatéral corrélé (corrélation=1) évoque une amélioration de détection lorsque la fréquence des stimuli cibles diminue (démasquage) : 0,97 dB à 4 kHz et 9,25 dB à 0,5 kHz. En PEA-P, les latences des ondes III et V se raccourcissent lorsqu’un bruit controlatéral corrélé ou non corrélé est ajouté (≈0,1 ms). En PEA-T, les amplitudes des ondes P1, N1 et des complexes P1N1 et N1P2 augmentent lorsqu’un bruit controlatéral corrélé ou non corrélé est ajouté. Enfin, l’amplitude de la MMN est plus conséquente lorsque le bruit controlatéral ajouté est corrélé (versus non corrélé). Conclusion : L’étude perceptive explicite l’importance des indices spectraux (antimasquage) et temporels (démasquage), pour améliorer la perception d’un signal initialement masqué. L’étude EEG suggère, quant à elle, un traitement sous-cortical influencé uniquement par les indices spectraux (antimasquage) et un traitement plus cortical influencé par les indices temporels (démasquage). / Background: Binaural unmasking is an essential process for understanding in noisy environments. This mechanism would involve the comparison of time and frequency cues throughout the hearing nerve pathways. However, there is no real consensus evoking a treatment of a binaural masking release at a subcortical and/or a cortical level. The purpose of this study is to investigate the time and frequency cues of the binaural unmasking through a perceptual study, and then through an electroencephalographic study (EEG).Materials and Methods: Normal hearing people were evaluated with a perceptive study to estimate the importance of the binaural unmasking according to 1) the frequency width of the contralateral noise (1 octave, 3 octaves or broadband), 2) the temporal coherence of bilateral noises (correlation equal to 0 or 1) and 3) the frequency of the target stimuli (0.5, 1, 2 and 4 kHz). Binaural unmasking was then evaluated with EEG by studying 1) early latencies (<10 ms, PEA-P), 2) late latencies (<50 ms, PEA-T) and 3), the mismatch wave (PEA- MMN). For these three EEG studies, the influence of the temporal coherence of bilateral noise was investigated.Results: The study shows a growing perceptive binaural unmasking when the frequency width of the contralateral noise increases. The addition of an uncorrelated contralateral noise (correlation = 0) results in a 1.28 dB detection enhancement, regardless of the frequency of the target stimuli (antimasking), while adding a contralateral correlated noise (correlation = 1) refers to a detection enhancement when the frequency of the target stimuli decreases (unmasking): 0.97 dB at 4 kHz and 9.25 dB at 0.5 kHz. The latencies of waves III and V are shortened when a contralateral correlated or uncorrelated noise is added (≈0,1 ms) in the PEA-P. The amplitudes of P1, N1 waves and P1N1 and N1P2 complex increase when contralateral correlated or uncorrelated noise is added in PEA-T. Finally, the amplitude of the MMN is higher when a contralateral correlated noise is added (versus an uncorrelated one).Conclusion: The perceptual study shows the significance of spectral cues (antimasking) and temporal cues (unmasking), to improve the perception of an initially masked signal. The EEG study suggests a subcortical treatment which is only influenced by spectral cues (antimasking) and a cortical processing, influenced by temporal cues (unmasking).

No description available.

This thesis focuses on the mapping of the microphone array’s response to match the characteristics of a human subject’s Head-Related Transfer Function (HRTF). The mapping of the response is first explored with a ‘monaural HRTF matching’ that filters the response independent of the arrival angles. For arbitrary array geometry with the listener external to the acoustic, the monaural HRTF matching did not provide listeners with enough spatial information to precisely localize sound sources. To correct this, a preprocessor control algorithm was added to the HRTF matching, a ‘binaural HRTF matching’ process. The binaural HRTF matching increased the listeners’ performance in perceiving the location of a sound source. With the addition of simulated head movement, the listeners’ perception increased by 20%. An issue with this approach is the use of HRTFs other than the listeners’ measured HRTF, creating a psychoacoustic based error in localization, i.e., front/back confusion. / Master of Science

The Short-Time Target Cancellation (STTC) algorithm, developed as part of this dissertation research, is a “Cocktail Party Problem” processor that can boost speech intelligibility for a target talker from a specified “look” direction, while suppressing the intelligibility of competing talkers. The algorithm holds promise for both automatic speech recognition and assistive listening device applications. The STTC algorithm operates on a frame-by-frame basis, leverages the computational efficiency of the Fast Fourier Transform (FFT), and is designed to run in real time. Notably, performance in objective measures of speech intelligibility and sound source segregation is comparable to that of the Ideal Binary Mask (IBM) and Ideal Ratio Mask (IRM). Because the STTC algorithm computes a time-frequency mask that can be applied independently to both the left and right signals, binaural cues for spatial hearing, including Interaural Time Differences (ITDs), Interaural Level Differences (ILDs) and spectral cues, can be preserved in potential hearing aid applications. A minimalist design for a proposed STTC Assistive Listening Device (ALD), consisting of six microphones embedded in the frame of a pair of eyeglasses, is presented and evaluated using virtual room acoustics and both objective and behavioral measures. The results suggest that the proposed STTC ALD can provide a significant speech intelligibility benefit in complex auditory scenes comprised of multiple spatially separated talkers. / 2020-10-22T00:00:00Z

Made available in DSpace on 2016-08-17T14:52:52Z (GMT). No. of bitstreams: 1 Edil James de Jesus Nascimento.PDF: 2709948 bytes, checksum: c8bf5634508e47328bd033c4d323f9c0 (MD5) Previous issue date: 2004-04-02 / The human hearing system is capable to accomplish different tasks that would be useful in engineering applications. One of them is the ability to separate sound sources, allowing the listener to "focus" a single sound source in a noisy environment. Great investments have been made in the development of technologies applied to the voice recognition by machines in real environment. For that, different techniques of processing computational have been proposed, for reduction of the ambient noise and improvement of the signal desired in complex acoustic environment (cocktail party). The model of the human hearing system motivates those techniques in their different phases. In this work, we developed an algorithm to improve the processing speech signal based on the binaural hearing model. After receiving the mixed signals, for two microphones, the algorithm increases the intelligibility of the signal of larger energy of one of the receivers. Using two speakers and considering that each one is closer of one of the microphones, we made use of the concepts of lateral inhibition and binaural masking, to recover the signal of speech of larger energy of one of the receivers. The algorithm was developed in platform matlab and it was compared with another without use the lateral inhibition in the recovery of the desired signal. The results, appraised through the calculation of the relative error and of the scale MOS, showed that the use of the lateral inhibition in the recovery of the signal, improves the relative error between the desired signal and the recovered signal and consequently the quality of the recovered signal. / O sistema auditivo humano é capaz de realizar diferentes tarefas que seriam úteis em aplicações de engenharia. Uma delas é a habilidade de separar fontes sonoras, permitindo a um ouvinte focar uma única fonte sonora em um ambiente ruidoso. Grandes investimentos têm sido feitos no desenvolvimento de tecnologias aplicadas ao reconhecimento de voz, por meio de máquinas, em ambientes reais. Para isso, diferentes técnicas de processamento computacional têm sido propostas para a redução do ruído ambiente e melhoramento do sinal desejado em ambiente acústico complexo (cocktail party). Essas técnicas são motivadas pelo modelo do sistema auditivo humano em suas diferentes fases. Neste trabalho, desenvolvemos um algoritmo para melhorar o processamento de um sinal de fala baseado no modelo auditivo binaural. Após receber os sinais misturados, por dois microfones, o algoritmo aumenta a inteligibilidade do sinal de maior energia de um dos receptores. Utilizando dois oradores e considerando que cada um está mais próximo de um dos receptores, fizemos uso dos conceitos de inibição lateral e mascaramento binaural, para recuperar o sinal de fala de maior energia de um dos receptores. O algoritmo foi desenvolvido sob a plataforma matlab e comparado com um outro sem a utilização da inibição lateral na recuperação do sinal desejado. Os resultados, avaliados através do cálculo do erro relativo e da escala MOS, mostraram que a utilização da inibição lateral na recuperação do sinal, melhora o erro relativo entre o sinal desejado e o sinal recuperado e conseqüentemente a qualidade do sinal recuperado.

At a cocktail party, one can choose to scan the room for conversations of interest, attend to a specific conversation partner, switch between conversation partners, or not attend to anything at all. The ability of the normal-functioning auditory system to flexibly listen in complex acoustic scenes plays a central role in solving the cocktail party problem (CPP). In contrast, certain demographics (e.g., individuals with hearing impairment or older adults) are unable to solve the CPP, leading to psychological ailments and reduced quality of life. Since the normal auditory system still outperforms machines in solving the CPP, an effective solution may be found by mimicking the normal-functioning auditory system. Spatial hearing likely plays an important role in CPP-processing in the auditory system. This thesis details the development of a biologically based approach to the CPP by modeling specific neural mechanisms underlying spatial tuning in the auditory cortex. First, we modeled bottom-up, stimulus-driven mechanisms using a multi-layer network model of the auditory system. To convert spike trains from the model output into audible waveforms, we designed a novel reconstruction method based on the estimation of time-frequency masks. We showed that our reconstruction method produced sounds with significantly higher intelligibility and quality than previous reconstruction methods. We also evaluated the algorithm's performance using a psychoacoustic study, and found that it provided the same amount of benefit to normal-hearing listeners as a current state-of-the-art acoustic beamforming algorithm. Finally, we modeled top-down, attention driven mechanisms that allowed the network to flexibly operate in different regimes, e.g., monitor the acoustic scene, attend to a specific target, and switch between attended targets. The model explains previous experimental observations, and proposes candidate neural mechanisms underlying flexible listening in cocktail-party scenarios. The strategies proposed here would benefit hearing-assistive devices for CPP processing (e.g., hearing aids), where users would benefit from switching between various modes of listening in different social situations. / 2022-05-19T00:00:00Z

Neurons communicate by action potentials. This process can be described by very detailed biochemical models of neuronal membrane and its channels, or by simpler phenomenological models of membrane potential (integrate-and- fire models) or even by very abstract models when only time of spikes are considered. We took one particular description - stochastic leaky integrate-and-fire model - and compared it with recorded in-vivo intracellular activity of the neuron. We estimated parameters of this model, compared how the model simulation corresponds with a real neuron. It can be concluded that the data are generally consistent with the model. At a more abstract level of description, the spike trains are analyzed without considering exact membrane voltage and one asks how the external stimulus is encoded in the spike train emitted by neurons. There are many neuronal codes described in literature and we focused on the open problem of neural code responsible for spatial hearing in mammals. Several theories explaining the experimental findings have been proposed and we suggest a specific variant of so called slope-encoding model. Neuronal circuit mimick- ing auditory pathway up to the first binaural neuron was constructed and experimental results were reproduced. Finally, we estimated the minimal number of such...

Neurons communicate by action potentials. This process can be described by very detailed biochemical models of neuronal membrane and its channels, or by simpler phenomenological models of membrane potential (integrate-and- fire models) or even by very abstract models when only time of spikes are considered. We took one particular description - stochastic leaky integrate-and-fire model - and compared it with recorded in-vivo intracellular activity of the neuron. We estimated parameters of this model, compared how the model simulation corresponds with a real neuron. It can be concluded that the data are generally consistent with the model. At a more abstract level of description, the spike trains are analyzed without considering exact membrane voltage and one asks how the external stimulus is encoded in the spike train emitted by neurons. There are many neuronal codes described in literature and we focused on the open problem of neural code responsible for spatial hearing in mammals. Several theories explaining the experimental findings have been proposed and we suggest a specific variant of so called slope-encoding model. Neuronal circuit mimick- ing auditory pathway up to the first binaural neuron was constructed and experimental results were reproduced. Finally, we estimated the minimal number of such...

The objective of the dissertation research is to investigate noise reduction methods for binaural hearing aids based on array and statistical signal processing and inspired by a human auditory model. In digital hearing aids, wide dynamic range compression (WDRC) is the most successful technique to deal with monaural hearing losses. This WDRC processing is usually performed after a monaural noise reduction algorithm. When hearing losses are present in both ears, i.e., a binaural hearing loss, independent monaural hearing aids have been shown not to be comfortable for most users, preferring a processing that involves synchronization between both hearing devices. In addition, psycho-acoustical studies have identified that under hostile environments, e.g., babble noise at very low SNR conditions, users prefer to use linear amplification rather than WDRC. In this sense, the noise reduction algorithm becomes an important component of a digital hearing aid to provide improvement in speech intelligibility and user comfort. Including a wireless link between both hearing aids offers new ways to implement more efficient methods to reduce the background noise and coordinate processing for the two ears. This approach, called binaural hearing aid, has been recently introduced in some commercial products but using very simple processing strategies. This research analyzes the existing binaural noise-reduction techniques, proposes novel perceptually-inspired methods based on blind source separation (BSS) and multichannel Wiener filter (MWF), and identifies different strategies for the real-time implementation of these methods. The proposed methods perform efficient spatial filtering, improve SNR and speech intelligibility, minimize block processing artifacts, and can be implemented in low-power architectures.