Abstract
A network model is proposed that uses a special node called epsilon -node. This model makes flexible path weight control of the network representing the acceptable sentences (ASN) possible by giving a score to the epsilon -node. The path weight control strategy is developed using a rule-based system, which has the ability to provide an adequate ASN according to the flow of conversation. A state-transition-network-based system is adopted in order to follow and adapt to the changing topics of conversation. A high-speed, highly reliable conversational speech understanding system is realized.
| Original language | English |
|---|---|
| Title of host publication | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
| Publisher | IEEE |
| Pages | 1589-1592 |
| Number of pages | 4 |
| Publication status | Published - 1986 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering
- Acoustics and Ultrasonics
Cite this
NETWORK MODEL DEALING WITH FOCUS OF CONVERSATION FOR SPEECH UNDERSTANDING SYSTEM. / Kobayashi, Tetsunori; Shirai, Katsuhiko.
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, 1986. p. 1589-1592.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - NETWORK MODEL DEALING WITH FOCUS OF CONVERSATION FOR SPEECH UNDERSTANDING SYSTEM.
AU - Kobayashi, Tetsunori
AU - Shirai, Katsuhiko
PY - 1986
Y1 - 1986
N2 - A network model is proposed that uses a special node called epsilon -node. This model makes flexible path weight control of the network representing the acceptable sentences (ASN) possible by giving a score to the epsilon -node. The path weight control strategy is developed using a rule-based system, which has the ability to provide an adequate ASN according to the flow of conversation. A state-transition-network-based system is adopted in order to follow and adapt to the changing topics of conversation. A high-speed, highly reliable conversational speech understanding system is realized.
AB - A network model is proposed that uses a special node called epsilon -node. This model makes flexible path weight control of the network representing the acceptable sentences (ASN) possible by giving a score to the epsilon -node. The path weight control strategy is developed using a rule-based system, which has the ability to provide an adequate ASN according to the flow of conversation. A state-transition-network-based system is adopted in order to follow and adapt to the changing topics of conversation. A high-speed, highly reliable conversational speech understanding system is realized.
UR - http://www.scopus.com/inward/record.url?scp=0022887461&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0022887461&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0022887461
SP - 1589
EP - 1592
BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PB - IEEE
ER -