Spectro-temporal modulation energy based mask for robust speaker identification
| dc.citation.epage | EL368 | en_US |
| dc.citation.issue | 5 | en_US |
| dc.citation.volume | 131 | en_US |
| dc.citation.woscount | 0 | |
| dc.contributor.author | Chi, Tai-Shih | en_US |
| dc.contributor.author | Lin, Ting-Han | en_US |
| dc.contributor.author | Hsu, Chung-Chien | en_US |
| dc.contributor.department | 電機工程學系 | zh_TW |
| dc.contributor.department | Department of Electrical and Computer Engineering | en_US |
| dc.date.accessioned | 2014-12-08T15:23:15Z | |
| dc.date.available | 2014-12-08T15:23:15Z | |
| dc.date.issued | 2012-05-01 | en_US |
| dc.description.abstract | Spectro-temporal modulations of speech encode speech structures and speaker characteristics. An algorithm which distinguishes speech from non-speech based on spectro-temporal modulation energies is proposed and evaluated in robust text-independent closed-set speaker identification simulations using the TIMIT and GRID corpora. Simulation results show the proposed method produces much higher speaker identification rates in all signal-to-noise ratio (SNR) conditions than the baseline system using mel-frequency cepstral coefficients. In addition, the proposed method also outperforms the system, which uses auditory-based nonnegative tensor cepstral coefficients [Q. Wu and L. Zhang, "Auditory sparse representation for robust speaker recognition based on tensor structure," EURASIP J. Audio, Speech, Music Process. 2008, 578612 (2008)], in low SNR (<= 10 dB) conditions. (C) 2012 Acoustical Society of America | en_US |
| dc.identifier.issn | 0001-4966 | en_US |
| dc.identifier.journal | JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA | en_US |
| dc.identifier.uri | https://ir.lib.nycu.edu.tw/handle/11536/16329 | |
| dc.identifier.wosnumber | WOS:000303601600003 | |
| dc.language.iso | en_US | en_US |
| dc.title | Spectro-temporal modulation energy based mask for robust speaker identification | en_US |
| dc.type | Article | en_US |