File Download
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: A study of switching state segmentation in segmental switching linear Gaussian hidden Markov models for robust speech recognition
| Title | A study of switching state segmentation in segmental switching linear Gaussian hidden Markov models for robust speech recognition |
|---|---|
| Authors | |
| Issue Date | 2004 |
| Publisher | IEEE, Signal Processing Society. |
| Citation | The 4th International Symposium on Chinese Spoken Language Processing, Hong Kong, China, 15-18 December 2004, p. 97-100 How to Cite? |
| Abstract | In our previous works, a switching linear Gaussian hidden Markov model (SLGHMM) and its segmental derivative, SSLGHMM, were proposed to cast the problem of modeling a noisy speech utterance in robust automatic speech recognition by a well-designed dynamic Bayesian network. An important issue of SSLGHMM is how to specify a switching state value for each frame of the feature vector in a given speech utterance. In this paper, we propose several approaches for addressing this issue and compare their performance on Aurora3 connected digit recognition tasks. |
| Persistent Identifier | http://hdl.handle.net/10722/45526 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Zhu, D | en_HK |
| dc.contributor.author | Huo, Q | en_HK |
| dc.contributor.author | Wu, J | en_HK |
| dc.date.accessioned | 2007-10-30T06:28:28Z | - |
| dc.date.available | 2007-10-30T06:28:28Z | - |
| dc.date.issued | 2004 | en_HK |
| dc.identifier.citation | The 4th International Symposium on Chinese Spoken Language Processing, Hong Kong, China, 15-18 December 2004, p. 97-100 | en_HK |
| dc.identifier.uri | http://hdl.handle.net/10722/45526 | - |
| dc.description.abstract | In our previous works, a switching linear Gaussian hidden Markov model (SLGHMM) and its segmental derivative, SSLGHMM, were proposed to cast the problem of modeling a noisy speech utterance in robust automatic speech recognition by a well-designed dynamic Bayesian network. An important issue of SSLGHMM is how to specify a switching state value for each frame of the feature vector in a given speech utterance. In this paper, we propose several approaches for addressing this issue and compare their performance on Aurora3 connected digit recognition tasks. | en_HK |
| dc.format.extent | 323608 bytes | - |
| dc.format.extent | 2385 bytes | - |
| dc.format.extent | 7254 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | text/plain | - |
| dc.format.mimetype | text/plain | - |
| dc.language | eng | en_HK |
| dc.publisher | IEEE, Signal Processing Society. | en_HK |
| dc.rights | ©2004 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. | - |
| dc.title | A study of switching state segmentation in segmental switching linear Gaussian hidden Markov models for robust speech recognition | en_HK |
| dc.type | Conference_Paper | en_HK |
| dc.description.nature | published_or_final_version | en_HK |
| dc.identifier.doi | 10.1109/CHINSL.2004.1409595 | en_HK |
| dc.identifier.hkuros | 101975 | - |