抄録
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.
| 元の言語 | English |
|---|---|
| ホスト出版物のタイトル | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
| 出版者 | IEEE |
| ページ | 1589-1592 |
| ページ数 | 4 |
| 出版物ステータス | Published - 1986 |
| 外部発表 | Yes |
Fingerprint
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering
- Acoustics and Ultrasonics
これを引用
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.研究成果: 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 -