Abstract
The authors propose a continuous-speech recognition method that uses an accurate and efficient parsing mechanism, an LR parser, and drives HMM (hidden Markov model) modules directly without any intervening structures such as a phoneme lattice. The method was tested in Japanese phrase recognition experiments. Two grammars were prepared, a general Japanese grammar and a task-specific grammar. The phrase recognition rate with the general grammar was 72% for top candidates and 95% for the five best candidates. With the task-specific grammar, recognition rate was 80% and 99%, respectively.
| Original language | English |
|---|---|
| Title of host publication | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
| Editors | Anon |
| Publisher | Publ by IEEE |
| Pages | 703-706 |
| Number of pages | 4 |
| Volume | 2 |
| Publication status | Published - 1989 |
| Externally published | Yes |
| Event | 1989 International Conference on Acoustics, Speech, and Signal Processing - Glasgow, Scotland Duration: 1989 May 23 → 1989 May 26 |
Other
| Other | 1989 International Conference on Acoustics, Speech, and Signal Processing |
|---|---|
| City | Glasgow, Scotland |
| Period | 89/5/23 → 89/5/26 |
Fingerprint
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering
- Acoustics and Ultrasonics
Cite this
HMM continuous speech recognition using predictive LR parsing. / Kita, Kenji; Kawabata, Takeshi; Saito, Hiroaki.
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. ed. / Anon. Vol. 2 Publ by IEEE, 1989. p. 703-706.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - HMM continuous speech recognition using predictive LR parsing
AU - Kita, Kenji
AU - Kawabata, Takeshi
AU - Saito, Hiroaki
PY - 1989
Y1 - 1989
N2 - The authors propose a continuous-speech recognition method that uses an accurate and efficient parsing mechanism, an LR parser, and drives HMM (hidden Markov model) modules directly without any intervening structures such as a phoneme lattice. The method was tested in Japanese phrase recognition experiments. Two grammars were prepared, a general Japanese grammar and a task-specific grammar. The phrase recognition rate with the general grammar was 72% for top candidates and 95% for the five best candidates. With the task-specific grammar, recognition rate was 80% and 99%, respectively.
AB - The authors propose a continuous-speech recognition method that uses an accurate and efficient parsing mechanism, an LR parser, and drives HMM (hidden Markov model) modules directly without any intervening structures such as a phoneme lattice. The method was tested in Japanese phrase recognition experiments. Two grammars were prepared, a general Japanese grammar and a task-specific grammar. The phrase recognition rate with the general grammar was 72% for top candidates and 95% for the five best candidates. With the task-specific grammar, recognition rate was 80% and 99%, respectively.
UR - http://www.scopus.com/inward/record.url?scp=0024934095&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0024934095&partnerID=8YFLogxK
M3 - Conference contribution
VL - 2
SP - 703
EP - 706
BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
A2 - Anon, null
PB - Publ by IEEE
ER -