Sparse Nonnegative Matrix Factorization Strategy for Cochlear Implants

Current cochlear implant (CI) strategies carry speech information via the waveform envelope in frequency subbands. CIs require efficient speech processing to maximize information transfer to the brain, especially in background noise, where the speech envelope is not robust to noise interference. In...

Full description

Bibliographic Details
Main Authors:	Hu, Hongmei, Lutman, Mark E., Ewert, Stephan D., Li, Guoping, Bleeck, Stefan
Format:	Online
Language:	English
Published:	SAGE Publications 2015
Online Access:	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4771045/

id	pubmed-4771045
recordtype	oai_dc
spelling	pubmed-47710452016-05-26 Sparse Nonnegative Matrix Factorization Strategy for Cochlear Implants Hu, Hongmei Lutman, Mark E. Ewert, Stephan D. Li, Guoping Bleeck, Stefan Special Issue Current cochlear implant (CI) strategies carry speech information via the waveform envelope in frequency subbands. CIs require efficient speech processing to maximize information transfer to the brain, especially in background noise, where the speech envelope is not robust to noise interference. In such conditions, the envelope, after decomposition into frequency bands, may be enhanced by sparse transformations, such as nonnegative matrix factorization (NMF). Here, a novel CI processing algorithm is described, which works by applying NMF to the envelope matrix (envelopogram) of 22 frequency channels in order to improve performance in noisy environments. It is evaluated for speech in eight-talker babble noise. The critical sparsity constraint parameter was first tuned using objective measures and then evaluated with subjective speech perception experiments for both normal hearing and CI subjects. Results from vocoder simulations with 10 normal hearing subjects showed that the algorithm significantly enhances speech intelligibility with the selected sparsity constraints. Results from eight CI subjects showed no significant overall improvement compared with the standard advanced combination encoder algorithm, but a trend toward improvement of word identification of about 10 percentage points at +15 dB signal-to-noise ratio (SNR) was observed in the eight CI subjects. Additionally, a considerable reduction of the spread of speech perception performance from 40% to 93% for advanced combination encoder to 80% to 100% for the suggested NMF coding strategy was observed. SAGE Publications 2015-12-16 /pmc/articles/PMC4771045/ /pubmed/26721919 http://dx.doi.org/10.1177/2331216515616941 Text en © The Author(s) 2015 http://creativecommons.org/licenses/by-nc/3.0/ This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 3.0 License (http://www.creativecommons.org/licenses/by-nc/3.0/) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access page(https://us.sagepub.com/en-us/nam/open-access-at-sage).
repository_type	Open Access Journal
institution_category	Foreign Institution
institution	US National Center for Biotechnology Information
building	NCBI PubMed
collection	Online Access
language	English
format	Online
author	Hu, Hongmei Lutman, Mark E. Ewert, Stephan D. Li, Guoping Bleeck, Stefan
spellingShingle	Hu, Hongmei Lutman, Mark E. Ewert, Stephan D. Li, Guoping Bleeck, Stefan Sparse Nonnegative Matrix Factorization Strategy for Cochlear Implants
author_facet	Hu, Hongmei Lutman, Mark E. Ewert, Stephan D. Li, Guoping Bleeck, Stefan
author_sort	Hu, Hongmei
title	Sparse Nonnegative Matrix Factorization Strategy for Cochlear Implants
title_short	Sparse Nonnegative Matrix Factorization Strategy for Cochlear Implants
title_full	Sparse Nonnegative Matrix Factorization Strategy for Cochlear Implants
title_fullStr	Sparse Nonnegative Matrix Factorization Strategy for Cochlear Implants
title_full_unstemmed	Sparse Nonnegative Matrix Factorization Strategy for Cochlear Implants
title_sort	sparse nonnegative matrix factorization strategy for cochlear implants
description	Current cochlear implant (CI) strategies carry speech information via the waveform envelope in frequency subbands. CIs require efficient speech processing to maximize information transfer to the brain, especially in background noise, where the speech envelope is not robust to noise interference. In such conditions, the envelope, after decomposition into frequency bands, may be enhanced by sparse transformations, such as nonnegative matrix factorization (NMF). Here, a novel CI processing algorithm is described, which works by applying NMF to the envelope matrix (envelopogram) of 22 frequency channels in order to improve performance in noisy environments. It is evaluated for speech in eight-talker babble noise. The critical sparsity constraint parameter was first tuned using objective measures and then evaluated with subjective speech perception experiments for both normal hearing and CI subjects. Results from vocoder simulations with 10 normal hearing subjects showed that the algorithm significantly enhances speech intelligibility with the selected sparsity constraints. Results from eight CI subjects showed no significant overall improvement compared with the standard advanced combination encoder algorithm, but a trend toward improvement of word identification of about 10 percentage points at +15 dB signal-to-noise ratio (SNR) was observed in the eight CI subjects. Additionally, a considerable reduction of the spread of speech perception performance from 40% to 93% for advanced combination encoder to 80% to 100% for the suggested NMF coding strategy was observed.
publisher	SAGE Publications
publishDate	2015
url	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4771045/
_version_	1613544741822005248

Sparse Nonnegative Matrix Factorization Strategy for Cochlear Implants

Similar Items