This paper discusses three approaches for combining an efficient LR parser and phoneme-context-dependent HMMs and compares them through continuous speech recognition experiments. In continuous speech recognition, phoneme-context-dependent allophonic models are considered very helpful for enhancing the recognition accuracy. They precisely represent allophonic variations caused by the difference in phoneme-contexts. With grammatical constraints based on a context free grammar (CFG), a generalized LR parser is one of the most efficient parsing algorithms for speech recognition. Therefore, the combination of allophonic models and a generalized LR parser is a powerful scheme enabling accurate and efficient speech recognition. In this paper, three phoneme-context-dependent LR parsing algorithms are proposed, which make it possible to drive allophonic HMMs. The algorithms are outlined as follows: (1) Algorithm for predicting the phonemic context dynamically in the LR parser using a phoneme-context-independent LR table. (2) Algorithm for converting an LR table into a phoneme-context-dependent LR table. (3) Algorithm for converting a CFG into a phoneme-context-dependent CFG. This paper also includes discussion of the results of recognition experiments, and a comparison of performance and efficiency of these three algorithms.
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
Akito NAGAI, Shigeki SAGAYAMA, Kenji KITA, Hideaki KIKUCHI, "Three Different LR Parsing Algorithms for Phoneme-Context-Dependent HMM-Based Continuous Speech Recognition" in IEICE TRANSACTIONS on Information,
vol. E76-D, no. 1, pp. 29-37, January 1993, doi: .
Abstract: This paper discusses three approaches for combining an efficient LR parser and phoneme-context-dependent HMMs and compares them through continuous speech recognition experiments. In continuous speech recognition, phoneme-context-dependent allophonic models are considered very helpful for enhancing the recognition accuracy. They precisely represent allophonic variations caused by the difference in phoneme-contexts. With grammatical constraints based on a context free grammar (CFG), a generalized LR parser is one of the most efficient parsing algorithms for speech recognition. Therefore, the combination of allophonic models and a generalized LR parser is a powerful scheme enabling accurate and efficient speech recognition. In this paper, three phoneme-context-dependent LR parsing algorithms are proposed, which make it possible to drive allophonic HMMs. The algorithms are outlined as follows: (1) Algorithm for predicting the phonemic context dynamically in the LR parser using a phoneme-context-independent LR table. (2) Algorithm for converting an LR table into a phoneme-context-dependent LR table. (3) Algorithm for converting a CFG into a phoneme-context-dependent CFG. This paper also includes discussion of the results of recognition experiments, and a comparison of performance and efficiency of these three algorithms.
URL: https://global.ieice.org/en_transactions/information/10.1587/e76-d_1_29/_p
Copy
@ARTICLE{e76-d_1_29,
author={Akito NAGAI, Shigeki SAGAYAMA, Kenji KITA, Hideaki KIKUCHI, },
journal={IEICE TRANSACTIONS on Information},
title={Three Different LR Parsing Algorithms for Phoneme-Context-Dependent HMM-Based Continuous Speech Recognition},
year={1993},
volume={E76-D},
number={1},
pages={29-37},
abstract={This paper discusses three approaches for combining an efficient LR parser and phoneme-context-dependent HMMs and compares them through continuous speech recognition experiments. In continuous speech recognition, phoneme-context-dependent allophonic models are considered very helpful for enhancing the recognition accuracy. They precisely represent allophonic variations caused by the difference in phoneme-contexts. With grammatical constraints based on a context free grammar (CFG), a generalized LR parser is one of the most efficient parsing algorithms for speech recognition. Therefore, the combination of allophonic models and a generalized LR parser is a powerful scheme enabling accurate and efficient speech recognition. In this paper, three phoneme-context-dependent LR parsing algorithms are proposed, which make it possible to drive allophonic HMMs. The algorithms are outlined as follows: (1) Algorithm for predicting the phonemic context dynamically in the LR parser using a phoneme-context-independent LR table. (2) Algorithm for converting an LR table into a phoneme-context-dependent LR table. (3) Algorithm for converting a CFG into a phoneme-context-dependent CFG. This paper also includes discussion of the results of recognition experiments, and a comparison of performance and efficiency of these three algorithms.},
keywords={},
doi={},
ISSN={},
month={January},}
Copy
TY - JOUR
TI - Three Different LR Parsing Algorithms for Phoneme-Context-Dependent HMM-Based Continuous Speech Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 29
EP - 37
AU - Akito NAGAI
AU - Shigeki SAGAYAMA
AU - Kenji KITA
AU - Hideaki KIKUCHI
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E76-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 1993
AB - This paper discusses three approaches for combining an efficient LR parser and phoneme-context-dependent HMMs and compares them through continuous speech recognition experiments. In continuous speech recognition, phoneme-context-dependent allophonic models are considered very helpful for enhancing the recognition accuracy. They precisely represent allophonic variations caused by the difference in phoneme-contexts. With grammatical constraints based on a context free grammar (CFG), a generalized LR parser is one of the most efficient parsing algorithms for speech recognition. Therefore, the combination of allophonic models and a generalized LR parser is a powerful scheme enabling accurate and efficient speech recognition. In this paper, three phoneme-context-dependent LR parsing algorithms are proposed, which make it possible to drive allophonic HMMs. The algorithms are outlined as follows: (1) Algorithm for predicting the phonemic context dynamically in the LR parser using a phoneme-context-independent LR table. (2) Algorithm for converting an LR table into a phoneme-context-dependent LR table. (3) Algorithm for converting a CFG into a phoneme-context-dependent CFG. This paper also includes discussion of the results of recognition experiments, and a comparison of performance and efficiency of these three algorithms.
ER -