Abstract
The ability to deploy speech recognition in mobile terminals, such as cell phones, has been limited to simple tasks due to restricted computational power and available memory. In this paper we present a new acoustic model based on vector quantization (VQ), which is better-suited for the limitations of the mobile environment. The proposed model is contrasted against finite state vector quantization (FSVQ); a commonly used technique is such environments. Performance enhancements include, temporal restrictions to state generation, a flexible number of vectors per state, and updates of the traditional state transition function to a higher order. Experimental results show that the new model improves the recognition rate and reduces the computation load.
| Original language | English (US) |
|---|---|
| Title of host publication | Conference Proceedings - IEEE SOUTHEASTCON |
| Editors | Y. Levy |
| Pages | 433-436 |
| Number of pages | 4 |
| State | Published - 2005 |
| Event | IEEE Southeastcon 2005: Excellence in Engineering, Science and Technology - Ft. Lauderdale, United Kingdom Duration: Apr 8 2005 → Apr 10 2005 |
Other
| Other | IEEE Southeastcon 2005: Excellence in Engineering, Science and Technology |
|---|---|
| Country | United Kingdom |
| City | Ft. Lauderdale |
| Period | 4/8/05 → 4/10/05 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
Cite this
A novel VQ-based speech recognition approach for mobile terminals. / He, Xing; Scordilis, Michael S; Li, Gongjun.
Conference Proceedings - IEEE SOUTHEASTCON. ed. / Y. Levy. 2005. p. 433-436.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A novel VQ-based speech recognition approach for mobile terminals
AU - He, Xing
AU - Scordilis, Michael S
AU - Li, Gongjun
PY - 2005
Y1 - 2005
N2 - The ability to deploy speech recognition in mobile terminals, such as cell phones, has been limited to simple tasks due to restricted computational power and available memory. In this paper we present a new acoustic model based on vector quantization (VQ), which is better-suited for the limitations of the mobile environment. The proposed model is contrasted against finite state vector quantization (FSVQ); a commonly used technique is such environments. Performance enhancements include, temporal restrictions to state generation, a flexible number of vectors per state, and updates of the traditional state transition function to a higher order. Experimental results show that the new model improves the recognition rate and reduces the computation load.
AB - The ability to deploy speech recognition in mobile terminals, such as cell phones, has been limited to simple tasks due to restricted computational power and available memory. In this paper we present a new acoustic model based on vector quantization (VQ), which is better-suited for the limitations of the mobile environment. The proposed model is contrasted against finite state vector quantization (FSVQ); a commonly used technique is such environments. Performance enhancements include, temporal restrictions to state generation, a flexible number of vectors per state, and updates of the traditional state transition function to a higher order. Experimental results show that the new model improves the recognition rate and reduces the computation load.
UR - http://www.scopus.com/inward/record.url?scp=27544438656&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=27544438656&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:27544438656
SP - 433
EP - 436
BT - Conference Proceedings - IEEE SOUTHEASTCON
A2 - Levy, Y.
ER -