Large vocabulary continuous Mandarin speech recognition using finite state machine

Author

Pan, Yi-Cheng ; Yu, Chia-Hsing ; Lee, Lin-shan

Author_Institution

Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan

fYear

2004

fDate

15-18 Dec. 2004

Firstpage

5

Lastpage

8

Abstract

The finite state transducer (FST), popularly used in the natural language processing (NLP) area to represent the grammar rules and the characteristics of a language, has been extensively used as the core in large vocabulary continuous speech recognition (LVCSR) in recent years. By means of FST, we can effectively compose the acoustic model, pronunciation lexicon, and language model to form a compact search space. In this paper, we present our approach to developing a LVCSR decoder using FST as the core. In addition, the traditional one-pass tree-copy search algorithm is also described for comparison in terms of speed, memory requirements and achieved character accuracy.

Keywords

finite state machines; natural languages; speech recognition; tree searching; vocabulary; FST; LVCSR decoder; NLP; acoustic model; character accuracy; compact search space; continuous Mandarin speech recognition; finite state machine; finite state transducer; grammar rules; language model; large vocabulary speech recognition; memory requirements; natural language processing; one-pass tree-copy search algorithm; pronunciation lexicon; Automata; Character recognition; Computer science; Decoding; Hidden Markov models; History; Natural language processing; Natural languages; Speech recognition; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Chinese Spoken Language Processing, 2004 International Symposium on

Print_ISBN

0-7803-8678-7

Type

conf

DOI

10.1109/CHINSL.2004.1409572

Filename

1409572