Show simple item record

dc.contributor.authorFujinaga, Katsuhisaen
dc.contributor.authorNakai, Mitsuruen
dc.contributor.authorShimodaira, Hiroshien
dc.contributor.authorSagayama, Shigekien
dc.date.accessioned2006-05-19T15:45:42Z
dc.date.available2006-05-19T15:45:42Z
dc.date.issued2001
dc.identifier.citationIn Proc. ICASSP 2001, May 2001.
dc.identifier.urihttp://hdl.handle.net/1842/1141
dc.description.abstractThis paper proposes a new class of hidden Markov model (HMM) called multiple-regression HMM (MRHMM) that utilizes auxiliary features such as fundamental frequency (F0) and speaking styles that affect spectral parameters to better model the acoustic features of phonemes. Though such auxiliary features are considered to be the factors that degrade the performance of speech recognizers, the proposed MR-HMM adapts its model parameters, i.e. mean vectors of output probability distributions, depending on these auxiliary information to improve the recognition accuracy. Formulation for parameter reestimation of MRHMM based on the EM algorithm is given in the paper. Experiments of speaker-dependent isolated word recognition demonstrated that MR-HMMs using F0 based auxiliary features reduced the error rates by more than 20% compared with the conventional HMMs.en
dc.format.extent101341 bytesen
dc.format.mimetypeapplication/pdfen
dc.language.isoen
dc.subjecthidden Markov modelen
dc.subjectmultiple-regression HMMen
dc.subjectspeechen
dc.titleMultiple-Regression Hidden Markov Modelen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record