A novel efficient decoding algorithm for CDHMM-based speech recognizer on chip

Author

Zhu, Xuan ; Chen, Yining ; Liu, Jia ; Liu, Runsheng

Author_Institution

Dept. of Electron. Eng., Tsinghua Univ., Beijing, China

Volume

2

fYear

2003

fDate

6-10 April 2003

Abstract

The efficiency of decoding algorithm is the main limitation of realizing a CDHMM-based large-vocabulary name dialing application on consumer electronic products. To solve this problem, a novel efficient decoding algorithm, TPVD (two-pass Viterbi decoding), is represented. By coarse matching in the first pass, several high-confidence candidates are selected from hundreds. Then, fine matching in the second pass runs on base of those high-confidence candidates. Compared with traditional Viterbi beam search, the hardware resource requirement is significantly reduced. Meanwhile, the recognition accuracy and speed are satisfactory. This conclusion has been proven in an embedded Mandarin 600-name dialing system.

Keywords

Viterbi decoding; consumer electronics; data compression; hidden Markov models; speech coding; speech recognition; CDHMM-based large-vocabulary; CDHMM-based speech recognizer; Viterbi beam search; chip; coarse matching; consumer electronic products; decoding algorithm efficiency; embedded Mandarin name dialing system; fine matching; hardware resource requirement; name dialing application; recognition accuracy; recognition speed; two-pass Viterbi decoding; Consumer electronics; Decoding; Hardware; Hidden Markov models; Mobile handsets; Personal digital assistants; Speech recognition; System-on-a-chip; Viterbi algorithm; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-7663-3

Type

conf

DOI

10.1109/ICASSP.2003.1202352

Filename

1202352