File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/0031-3203(94)00117-5
- Scopus: eid_2-s2.0-0029288597
- WOS: WOS:A1995QR65900003
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Contextual vector quantization for speech recognition with discrete hidden Markov model
Title | Contextual vector quantization for speech recognition with discrete hidden Markov model |
---|---|
Authors | |
Keywords | Contextual information Vector quantization Hidden markov model markov random field Automatic speech recognition |
Issue Date | 1995 |
Publisher | Elsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pr |
Citation | Pattern Recognition, 1995, v. 28 n. 4, p. 513-517 How to Cite? |
Abstract | By using formulation of the finite mixture distribution identification, in this paper, several alternatives to the conventional LBG VQ method are investigated. A contextual VQ method based on the Markov Random Field (MRF) theory is proposed to model the speech feature vector space. Its superiority is confirmed by a series of comparative experiments in a speaker independent isolated word recognition task by using different VQ schemes as the front-end of DHMM. The motivation to use MRF to model the contextual dependence information in the underlying speech production process can be readily extended to acoustic modeling of the basic speech units in speech recognition. |
Persistent Identifier | http://hdl.handle.net/10722/267841 |
ISSN | 2023 Impact Factor: 7.5 2023 SCImago Journal Rankings: 2.732 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Huo, Q | - |
dc.contributor.author | Chan, C | - |
dc.date.accessioned | 2019-03-05T03:46:39Z | - |
dc.date.available | 2019-03-05T03:46:39Z | - |
dc.date.issued | 1995 | - |
dc.identifier.citation | Pattern Recognition, 1995, v. 28 n. 4, p. 513-517 | - |
dc.identifier.issn | 0031-3203 | - |
dc.identifier.uri | http://hdl.handle.net/10722/267841 | - |
dc.description.abstract | By using formulation of the finite mixture distribution identification, in this paper, several alternatives to the conventional LBG VQ method are investigated. A contextual VQ method based on the Markov Random Field (MRF) theory is proposed to model the speech feature vector space. Its superiority is confirmed by a series of comparative experiments in a speaker independent isolated word recognition task by using different VQ schemes as the front-end of DHMM. The motivation to use MRF to model the contextual dependence information in the underlying speech production process can be readily extended to acoustic modeling of the basic speech units in speech recognition. | - |
dc.language | eng | - |
dc.publisher | Elsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pr | - |
dc.relation.ispartof | Pattern Recognition | - |
dc.subject | Contextual information | - |
dc.subject | Vector quantization | - |
dc.subject | Hidden markov model markov random field | - |
dc.subject | Automatic speech recognition | - |
dc.title | Contextual vector quantization for speech recognition with discrete hidden Markov model | - |
dc.type | Article | - |
dc.identifier.email | Chan, C: cchan@csis.hku.hk | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/0031-3203(94)00117-5 | - |
dc.identifier.scopus | eid_2-s2.0-0029288597 | - |
dc.identifier.hkuros | 533 | - |
dc.identifier.hkuros | 20275 | - |
dc.identifier.volume | 28 | - |
dc.identifier.issue | 4 | - |
dc.identifier.spage | 513 | - |
dc.identifier.epage | 517 | - |
dc.identifier.isi | WOS:A1995QR65900003 | - |
dc.publisher.place | Netherlands | - |
dc.identifier.issnl | 0031-3203 | - |