File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1006/csla.1996.0006
- Scopus: eid_2-s2.0-0030121298
- WOS: WOS:A1996VC06400002
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: A study on the use of bi-directional contextual dependence in Markov Random Field-based Acoustic Modelling for speech recognition
Title | A study on the use of bi-directional contextual dependence in Markov Random Field-based Acoustic Modelling for speech recognition |
---|---|
Authors | |
Keywords | Acoustics Algorithms Markov processes Mathematical models Parallel processing systems |
Issue Date | 1996 |
Publisher | Academic Press. The Journal's web site is located at http://www.elsevier.com/locate/csl |
Citation | Computer Speech and Language, 1996, v. 10 n. 2, p. 95-105 How to Cite? |
Abstract | In this paper, by using the formulation of the missing-data problem, a general framework for statistical acoustic modelling of speech is presented. With the motivation of utilizing bi-directional contextual dependence in acoustic modelling, a bi-directional hidden Markov modelling approach for speech recognition is studied and the importance of the bi-directional contextual dependence for speech recognition is identified by a series of comparative experiments. Furthermore, hidden Markov random field (MRF)-based acoustic modelling techniques using our previously proposed contextual vector quantization (CVQ) method and iterated conditional modes (ICM) algorithm, which is very suitable for parallel processing implementation, are also attempted. Their viability is confirmed by a series of preliminary experiments in a speaker-independent isolated English letter recognition task. |
Persistent Identifier | http://hdl.handle.net/10722/224735 |
ISSN | 2023 Impact Factor: 3.1 2023 SCImago Journal Rankings: 1.050 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Huo, Q | - |
dc.contributor.author | Chan, C | - |
dc.date.accessioned | 2016-04-13T08:18:51Z | - |
dc.date.available | 2016-04-13T08:18:51Z | - |
dc.date.issued | 1996 | - |
dc.identifier.citation | Computer Speech and Language, 1996, v. 10 n. 2, p. 95-105 | - |
dc.identifier.issn | 0885-2308 | - |
dc.identifier.uri | http://hdl.handle.net/10722/224735 | - |
dc.description.abstract | In this paper, by using the formulation of the missing-data problem, a general framework for statistical acoustic modelling of speech is presented. With the motivation of utilizing bi-directional contextual dependence in acoustic modelling, a bi-directional hidden Markov modelling approach for speech recognition is studied and the importance of the bi-directional contextual dependence for speech recognition is identified by a series of comparative experiments. Furthermore, hidden Markov random field (MRF)-based acoustic modelling techniques using our previously proposed contextual vector quantization (CVQ) method and iterated conditional modes (ICM) algorithm, which is very suitable for parallel processing implementation, are also attempted. Their viability is confirmed by a series of preliminary experiments in a speaker-independent isolated English letter recognition task. | - |
dc.language | eng | - |
dc.publisher | Academic Press. The Journal's web site is located at http://www.elsevier.com/locate/csl | - |
dc.relation.ispartof | Computer Speech and Language | - |
dc.rights | Posting accepted manuscript (postprint): © <year>. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/ | - |
dc.subject | Acoustics | - |
dc.subject | Algorithms | - |
dc.subject | Markov processes | - |
dc.subject | Mathematical models | - |
dc.subject | Parallel processing systems | - |
dc.title | A study on the use of bi-directional contextual dependence in Markov Random Field-based Acoustic Modelling for speech recognition | - |
dc.type | Article | - |
dc.identifier.email | Huo, Q: qhuo@itl.atr.co.jp | - |
dc.identifier.email | Chan, C: cchan@cs.hku.hk | - |
dc.identifier.doi | 10.1006/csla.1996.0006 | - |
dc.identifier.scopus | eid_2-s2.0-0030121298 | - |
dc.identifier.hkuros | 20955 | - |
dc.identifier.volume | 10 | - |
dc.identifier.issue | 2 | - |
dc.identifier.spage | 95 | - |
dc.identifier.epage | 105 | - |
dc.identifier.isi | WOS:A1996VC06400002 | - |
dc.publisher.place | United Kingdom | - |
dc.identifier.issnl | 0885-2308 | - |