Audio processing conducted in the speech enhancement stage plays a crucial role in improving speech intelligibility, especially in noisy environments. 1 IntroductionĪ typical signal processing chain in a hearing aid includes speech enhancement followed by amplification and dynamic range compression for hearing loss compensation to alleviate recruitment effects, as well as feedback suppression to allow sufficiently high amplification. This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Nevertheless, our approach performs well in all acoustic scenes tested and varying SNRs and reliably detects incorrect spatial filtering angles. The system is not adapted to the environment and does not require a-priori information about the acoustic scene or a reference signal to estimate the quality of the enhanced speech signal. We show that two of the three ASQMs (M-Measure, MaP filtering) are suited to reliably identify the speech target in different conditions. The effects of incorrect spatial filtering and noise were analyzed. We tested the approach in four acoustic scenes with one speaker and either a localized or a diffuse noise source at various signal-to-noise ratios (SNR) in anechoic or reverberant conditions. Three ASR-based speech quality measures (ASQM) are explored: entropy, mean temporal distance (M-Measure), matched phoneme (MaP) filtering. The measure of speech quality is based on phoneme representations obtained from a deep neural network, which is part of a hybrid automatic speech recognition (ASR) system. The DOA estimator provides spatial sound source probability in the frontal horizontal plane. We have combined an estimator for the direction of arrival (DOA), featuring high spatial resolution but no specialization to speech, with a measure of speech quality with low spatial resolution obtained after directional filtering. In this study, we therefore propose an approach for spatial detection of speech based on sound source localization and blind optimization of speech enhancement for binaural hearing aids. * Corresponding author: hearing aids are limited with respect to speech-specific optimization for spatial sound sources to perform speech enhancement. Meyer 4 ,2Īuditory Signal Processing & Hearing Devices, Carl von Ossietzky University, 26111Ĭenter for Language and Speech Processing, Johns Hopkins University, Baltimore, MDĬommunication Acoustics, Carl von Ossietzky University, 26111 Hendrik Kayser 1 ,2 *, Hynek Hermansky 3 and Bernd T.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |