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 |
|---|---|
| Pages (from-to) | 703-706 |
| Number of pages | 4 |
| Journal | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
| Volume | 2 |
| Publication status | Published - 1989 Dec 1 |
| Externally published | Yes |
| Event | 1989 International Conference on Acoustics, Speech, and Signal Processing - Glasgow, Scotland Duration: 1989 May 23 → 1989 May 26 |
ASJC Scopus subject areas
- Software
- Signal Processing
- Electrical and Electronic Engineering
Fingerprint Dive into the research topics of 'HMM continuous speech recognition using predictive LR parsing'. Together they form a unique fingerprint.
Cite this
Kita, K., Kawabata, T., & Saito, H. (1989). HMM continuous speech recognition using predictive LR parsing. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2, 703-706.