Search algorithm that merges candidates in meaning level for very large vocabulary spontaneous speech recognition

Author

Minami, Yasuhiro ; Shikano, Kiyohiro ; Takahashi, Satoshi ; Yamada, Tomokazu

Author_Institution

NTT Human Interface Labs., Tokyo, Japan

Volume

ii

fYear

1994

fDate

19-22 Apr 1994

Abstract

The paper describes an efficient search algorithm for spontaneous speech recognition. This algorithm merges candidates that have the same meaning in beam search. To do this effectively, the authors change their phoneme-synchronous search algorithm into a quasi-frame-synchronous one. The algorithm is evaluated using a telephone directory assistance task containing more than 70000 subscriber names. The average sentence understanding rate for eight speakers is improved from 58% to 65% by merging candidates at the meaning level

Keywords

context-free grammars; natural language interfaces; search problems; speech recognition; telephony; phoneme-synchronous search algorithm; quasi-frame-synchronous search algorithm; search algorithm; sentence understanding rate; spontaneous speech recognition; subscriber names; telephone directory assistance task; Cities and towns; Hidden Markov models; Humans; Laboratories; Merging; Probability; Speech recognition; Telephony; Viterbi algorithm; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on

Conference_Location

Adelaide, SA

ISSN

1520-6149

Print_ISBN

0-7803-1775-0

Type

conf

DOI

10.1109/ICASSP.1994.389699

Filename

389699