A Large Vocabulary Continuous Speech Recognition System with High Predictability

Minoru SHIGENAGA; Yoshihiro SEKIGUCHI; Takehiro YAMAGUCHI; Ryouta MASUDA

A Large Vocabulary Continuous Speech Recognition System with High Predictability

Minoru SHIGENAGA, Yoshihiro SEKIGUCHI, Takehiro YAMAGUCHI, Ryouta MASUDA

Full Text Views

0

Cite this

Summary :

A large vocabulary (with 1019 words and 1382 kinds of inflectional endings) continuous speech recognition system with high predictability applicable to any task and have an unsupervised speaker adaptation capability is described. Phoneme identification is based on various features. Speaker adaptation is done using reliable identified phonemes. Using prosodic information, phrase boundaries are detected. The syntactic analyzer uses a syntactic state transition network and outputs syntactic interpretations. The semantic analyser deals with the meaning of each word, the dependency relationships between words, the extended case structures of predicates, associative function, in universally applicable forms. The extended case grammar with a set of four-items of the case structure and the dependency relationships between words are based on semantic attributes of relating words, and realizes, together with associative function, universally applicable high prediction capability.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E74-A No.7 pp.1817-1825

Publication Date: 1991/07/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Continuous Speech Recognition and Understanding)

Category: Continuous Speech Recognition

Authors

Minoru SHIGENAGA
Yoshihiro SEKIGUCHI
Takehiro YAMAGUCHI
Ryouta MASUDA

Keyword

Cite this

Copy

Minoru SHIGENAGA, Yoshihiro SEKIGUCHI, Takehiro YAMAGUCHI, Ryouta MASUDA, "A Large Vocabulary Continuous Speech Recognition System with High Predictability" in IEICE TRANSACTIONS on Fundamentals, vol. E74-A, no. 7, pp. 1817-1825, July 1991, doi: .
Abstract: A large vocabulary (with 1019 words and 1382 kinds of inflectional endings) continuous speech recognition system with high predictability applicable to any task and have an unsupervised speaker adaptation capability is described. Phoneme identification is based on various features. Speaker adaptation is done using reliable identified phonemes. Using prosodic information, phrase boundaries are detected. The syntactic analyzer uses a syntactic state transition network and outputs syntactic interpretations. The semantic analyser deals with the meaning of each word, the dependency relationships between words, the extended case structures of predicates, associative function, in universally applicable forms. The extended case grammar with a set of four-items of the case structure and the dependency relationships between words are based on semantic attributes of relating words, and realizes, together with associative function, universally applicable high prediction capability.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e74-a_7_1817/_p

Copy

@ARTICLE{e74-a_7_1817,
author={Minoru SHIGENAGA, Yoshihiro SEKIGUCHI, Takehiro YAMAGUCHI, Ryouta MASUDA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Large Vocabulary Continuous Speech Recognition System with High Predictability},
year={1991},
volume={E74-A},
number={7},
pages={1817-1825},
abstract={A large vocabulary (with 1019 words and 1382 kinds of inflectional endings) continuous speech recognition system with high predictability applicable to any task and have an unsupervised speaker adaptation capability is described. Phoneme identification is based on various features. Speaker adaptation is done using reliable identified phonemes. Using prosodic information, phrase boundaries are detected. The syntactic analyzer uses a syntactic state transition network and outputs syntactic interpretations. The semantic analyser deals with the meaning of each word, the dependency relationships between words, the extended case structures of predicates, associative function, in universally applicable forms. The extended case grammar with a set of four-items of the case structure and the dependency relationships between words are based on semantic attributes of relating words, and realizes, together with associative function, universally applicable high prediction capability.},
keywords={},
doi={},
ISSN={},
month={July},}

Copy

TY - JOUR
TI - A Large Vocabulary Continuous Speech Recognition System with High Predictability
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1817
EP - 1825
AU - Minoru SHIGENAGA
AU - Yoshihiro SEKIGUCHI
AU - Takehiro YAMAGUCHI
AU - Ryouta MASUDA
PY - 1991
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E74-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 1991
AB - A large vocabulary (with 1019 words and 1382 kinds of inflectional endings) continuous speech recognition system with high predictability applicable to any task and have an unsupervised speaker adaptation capability is described. Phoneme identification is based on various features. Speaker adaptation is done using reliable identified phonemes. Using prosodic information, phrase boundaries are detected. The syntactic analyzer uses a syntactic state transition network and outputs syntactic interpretations. The semantic analyser deals with the meaning of each word, the dependency relationships between words, the extended case structures of predicates, associative function, in universally applicable forms. The extended case grammar with a set of four-items of the case structure and the dependency relationships between words are based on semantic attributes of relating words, and realizes, together with associative function, universally applicable high prediction capability.
ER -