Sparsity level in a non-negative matrix factorization based speech strategy in cochlear implants
2012 (English)In: 2012 Proceedings Of The 20th European Signal Processing Conference (EUSIPCO), IEEE Computer Society, 2012, 2432-2436 p.Conference paper (Refereed)
Non-negative matrix factorization (NMF) has increasinglybeen used as a tool in signal processing in the last years, butit has not been used in the cochlear implants (CIs). Toimprove the performance of CIs in noisy environments, anovel sparse strategy is proposed by applying NMF onenvelops of 22 channels. In the new algorithm, the noisyspeech is first transferred to the time-frequency domain viaa 22- channel filter bank and the envelope in each frequencychannel is extracted; secondly, NMF is applied to theenvelope matrix (envelopegram); finally, the sparsitycondition is applied to the coefficient matrix to get moresparse representation. Speech reception threshold (SRT)subjective experiment was performed in combination withfive objective measurements in order to choose the properparameters for the sparse NMF model.
Place, publisher, year, edition, pages
IEEE Computer Society, 2012. 2432-2436 p.
, European Signal Proceedings Conference, ISSN 2076-1465
Non-negative matrix factorization, cochlear implants, sparse coding, objective measurements, speech perception threshold
Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:kth:diva-105197ISI: 000310623800489ScopusID: 2-s2.0-84869745006ISBN: 978-1-4673-1068-0OAI: oai:DiVA.org:kth-105197DiVA: diva2:570296
European Signal Process. Conf. (EUSIPCO), 27-31 Aug. 2012, Bucharest, Romania
FunderICT - The Next Generation
QC 201211202012-11-202012-11-192013-04-15Bibliographically approved