File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.3934/jimo.2009.5.671
- Scopus: eid_2-s2.0-68049111237
- WOS: WOS:000269239600018
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: A multi-filter system for speech enhancement under low signal-to-noise ratios
Title | A multi-filter system for speech enhancement under low signal-to-noise ratios | ||||||
---|---|---|---|---|---|---|---|
Authors | |||||||
Keywords | Noise Reduction Optimization Speech Echancement Speech Recognition | ||||||
Issue Date | 2009 | ||||||
Publisher | American Institute of Mathematical Sciences. The Journal's web site is located at http://aimsciences.org/journals/jimo/description.htm | ||||||
Citation | Journal Of Industrial And Management Optimization, 2009, v. 5 n. 3, p. 671-682 How to Cite? | ||||||
Abstract | In this paper, the problem of deteriorating performance of speech recognition under very low signal-to-noise ratios (SNR) is considered. In particular, for a given pre-trained speech recognizer and for a finite set of speech commands, we show that popular noise reduction methods have a mixed performance in speech recognition accuracy under very low SNR. Although most noise reduction methods are attempting to reduce speech distortion or to increase noise suppression, it does not necessarily improve speech recognition accuracy very much due to the complexity of the recognizer. We propose a new hybrid algorithm to optimize on the speech recognition accuracy directly by mixing different noise reduction methods together. We show that this method can indeed improve the accuracy significantly. | ||||||
Persistent Identifier | http://hdl.handle.net/10722/155919 | ||||||
ISSN | 2023 Impact Factor: 1.2 2023 SCImago Journal Rankings: 0.364 | ||||||
ISI Accession Number ID |
Funding Information: The first author is supported by the Research Grants Council of HKSAR (PolyU 7191/06E) and the Research Committee of the Hong Kong Polytechnic University. | ||||||
References |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yiu, KFC | en_US |
dc.contributor.author | Chan, KY | en_US |
dc.contributor.author | Low, SY | en_US |
dc.contributor.author | Nordholm, S | en_US |
dc.date.accessioned | 2012-08-08T08:38:24Z | - |
dc.date.available | 2012-08-08T08:38:24Z | - |
dc.date.issued | 2009 | en_US |
dc.identifier.citation | Journal Of Industrial And Management Optimization, 2009, v. 5 n. 3, p. 671-682 | en_US |
dc.identifier.issn | 1547-5816 | en_US |
dc.identifier.uri | http://hdl.handle.net/10722/155919 | - |
dc.description.abstract | In this paper, the problem of deteriorating performance of speech recognition under very low signal-to-noise ratios (SNR) is considered. In particular, for a given pre-trained speech recognizer and for a finite set of speech commands, we show that popular noise reduction methods have a mixed performance in speech recognition accuracy under very low SNR. Although most noise reduction methods are attempting to reduce speech distortion or to increase noise suppression, it does not necessarily improve speech recognition accuracy very much due to the complexity of the recognizer. We propose a new hybrid algorithm to optimize on the speech recognition accuracy directly by mixing different noise reduction methods together. We show that this method can indeed improve the accuracy significantly. | en_US |
dc.language | eng | en_US |
dc.publisher | American Institute of Mathematical Sciences. The Journal's web site is located at http://aimsciences.org/journals/jimo/description.htm | en_US |
dc.relation.ispartof | Journal of Industrial and Management Optimization | en_US |
dc.subject | Noise Reduction | en_US |
dc.subject | Optimization | en_US |
dc.subject | Speech Echancement | en_US |
dc.subject | Speech Recognition | en_US |
dc.title | A multi-filter system for speech enhancement under low signal-to-noise ratios | en_US |
dc.type | Article | en_US |
dc.identifier.email | Yiu, KFC:cedric@hkucc.hku.hk | en_US |
dc.identifier.authority | Yiu, KFC=rp00206 | en_US |
dc.description.nature | link_to_subscribed_fulltext | en_US |
dc.identifier.doi | 10.3934/jimo.2009.5.671 | en_US |
dc.identifier.scopus | eid_2-s2.0-68049111237 | en_US |
dc.relation.references | http://www.scopus.com/mlt/select.url?eid=2-s2.0-68049111237&selection=ref&src=s&origin=recordpage | en_US |
dc.identifier.volume | 5 | en_US |
dc.identifier.issue | 3 | en_US |
dc.identifier.spage | 671 | en_US |
dc.identifier.epage | 682 | en_US |
dc.identifier.isi | WOS:000269239600018 | - |
dc.publisher.place | United States | en_US |
dc.identifier.scopusauthorid | Yiu, KFC=24802813000 | en_US |
dc.identifier.scopusauthorid | Chan, KY=25639498200 | en_US |
dc.identifier.scopusauthorid | Low, SY=7102636488 | en_US |
dc.identifier.scopusauthorid | Nordholm, S=7005690573 | en_US |
dc.identifier.issnl | 1547-5816 | - |