This paper describes a continuous speech recognition system using two-level LR parsing and phone based HMMs. ATR has already implemented a predictive LR parsing algorithm in an HMM-based speech recognition system for Japanese. However, up to now, this system has used only intra-phrase grammatical constraints. In Japanese, a sentence is composed of several phrases and thus, two kinds of grammars, namely an intra-phrase grammar and an inter-phrase grammar, are sufficient for recognizing sentences. Two-level LR parsing makes it possible to use not only intra-phrase grammatical constraints but also inter-phrase grammatical constraints during speech recognition. The system is applied to Japanese sentence recognition where sentences were uttered phrase by phrase, and attains a word accuracy of 95.9% and a sentence accuracy of 84.7%.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Kenji KITA, Toshiyuki TAKEZAWA, Tsuyoshi MORIMOTO, "Continuous Speech Recognition Using Two-Level LR Parsing" in IEICE TRANSACTIONS on Fundamentals,
vol. E74-A, no. 7, pp. 1806-1810, July 1991, doi: .
Abstract: This paper describes a continuous speech recognition system using two-level LR parsing and phone based HMMs. ATR has already implemented a predictive LR parsing algorithm in an HMM-based speech recognition system for Japanese. However, up to now, this system has used only intra-phrase grammatical constraints. In Japanese, a sentence is composed of several phrases and thus, two kinds of grammars, namely an intra-phrase grammar and an inter-phrase grammar, are sufficient for recognizing sentences. Two-level LR parsing makes it possible to use not only intra-phrase grammatical constraints but also inter-phrase grammatical constraints during speech recognition. The system is applied to Japanese sentence recognition where sentences were uttered phrase by phrase, and attains a word accuracy of 95.9% and a sentence accuracy of 84.7%.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e74-a_7_1806/_p
Copy
@ARTICLE{e74-a_7_1806,
author={Kenji KITA, Toshiyuki TAKEZAWA, Tsuyoshi MORIMOTO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Continuous Speech Recognition Using Two-Level LR Parsing},
year={1991},
volume={E74-A},
number={7},
pages={1806-1810},
abstract={This paper describes a continuous speech recognition system using two-level LR parsing and phone based HMMs. ATR has already implemented a predictive LR parsing algorithm in an HMM-based speech recognition system for Japanese. However, up to now, this system has used only intra-phrase grammatical constraints. In Japanese, a sentence is composed of several phrases and thus, two kinds of grammars, namely an intra-phrase grammar and an inter-phrase grammar, are sufficient for recognizing sentences. Two-level LR parsing makes it possible to use not only intra-phrase grammatical constraints but also inter-phrase grammatical constraints during speech recognition. The system is applied to Japanese sentence recognition where sentences were uttered phrase by phrase, and attains a word accuracy of 95.9% and a sentence accuracy of 84.7%.},
keywords={},
doi={},
ISSN={},
month={July},}
Copy
TY - JOUR
TI - Continuous Speech Recognition Using Two-Level LR Parsing
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1806
EP - 1810
AU - Kenji KITA
AU - Toshiyuki TAKEZAWA
AU - Tsuyoshi MORIMOTO
PY - 1991
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E74-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 1991
AB - This paper describes a continuous speech recognition system using two-level LR parsing and phone based HMMs. ATR has already implemented a predictive LR parsing algorithm in an HMM-based speech recognition system for Japanese. However, up to now, this system has used only intra-phrase grammatical constraints. In Japanese, a sentence is composed of several phrases and thus, two kinds of grammars, namely an intra-phrase grammar and an inter-phrase grammar, are sufficient for recognizing sentences. Two-level LR parsing makes it possible to use not only intra-phrase grammatical constraints but also inter-phrase grammatical constraints during speech recognition. The system is applied to Japanese sentence recognition where sentences were uttered phrase by phrase, and attains a word accuracy of 95.9% and a sentence accuracy of 84.7%.
ER -