DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jin, MH | ko |
dc.contributor.author | Soong, FK | ko |
dc.contributor.author | Yoo, Chang Dong | ko |
dc.date.accessioned | 2013-03-06T22:01:00Z | - |
dc.date.available | 2013-03-06T22:01:00Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2007-11 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, v.15, no.8, pp.2476 - 2484 | - |
dc.identifier.issn | 1558-7916 | - |
dc.identifier.uri | http://hdl.handle.net/10203/88611 | - |
dc.description.abstract | This paper proposes a syllable-lattice-based speaker verification algorithm for Mandarin Chinese input. For each speech utterance, a syllable lattice is generated with a speaker-independent large-vocabulary continuous speech recognition system in free syllable decoding. The verification decision is made based upon the likelihood ratio between a target-speaker model and a speaker-independent background model, computed on the decoded syllable lattice. The likelihood function is calculated efficiently in a forward algorithm by considering all paths in the lattice. The proposed algorithm was evaluated using a Mandarin Chinese database, where 1832 true and 26 250 impostor trials were recorded by 19 target speakers and 180 impostors. The average duration of each trial is 2 s long without silence. The target-speaker model was adapted from the speaker-independent background model using enrollment data of two minutes with silence. The proposed algorithm achieved an equal-error rate of 0.857% which is beter than 1.21% of the hidden Markov model-based speaker verification algorithm without using syllable lattices. The equal-error rate was further reduced to 0.617% by incorporating the Goussian mixture model-universal background model algorithm with 2048 Gaussian kernels whose equal error rate is 0.990%. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | HIDDEN MARKOV-MODELS | - |
dc.subject | MANDARIN CHINESE | - |
dc.subject | RECOGNITION | - |
dc.subject | ADAPTATION | - |
dc.subject | SPEECH | - |
dc.title | A syllable lattice approach to speaker verification | - |
dc.type | Article | - |
dc.identifier.wosid | 000250282800026 | - |
dc.identifier.scopusid | 2-s2.0-57349174331 | - |
dc.type.rims | ART | - |
dc.citation.volume | 15 | - |
dc.citation.issue | 8 | - |
dc.citation.beginningpage | 2476 | - |
dc.citation.endingpage | 2484 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING | - |
dc.identifier.doi | 10.1109/TASL.2007.906181 | - |
dc.contributor.localauthor | Yoo, Chang Dong | - |
dc.contributor.nonIdAuthor | Jin, MH | - |
dc.contributor.nonIdAuthor | Soong, FK | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | lattice-based speaker adaptation | - |
dc.subject.keywordAuthor | lattice rescoring | - |
dc.subject.keywordAuthor | Mandarin Chinese | - |
dc.subject.keywordAuthor | speaker recognition. | - |
dc.subject.keywordPlus | HIDDEN MARKOV-MODELS | - |
dc.subject.keywordPlus | MANDARIN CHINESE | - |
dc.subject.keywordPlus | RECOGNITION | - |
dc.subject.keywordPlus | ADAPTATION | - |
dc.subject.keywordPlus | SPEECH | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.