A new connected word recognition algorithm based on HMM/LVQ segmentation and LVQ classification

Author

Ramesh, Padma ; Katagiri, Shigeru ; Lee, Chin-Hui

Author_Institution

AT&T Bell Lab., Murray Hill, NJ, USA

fYear

1991

fDate

14-17 Apr 1991

Firstpage

113

Abstract

The authors present a novel HMM/LVQ (hidden Markov model/learning vector quantization) hybrid algorithm for connected word recognition (CWR). They show that, for combining both the discriminative power of LVQ and the capability of modeling temporal variations, of speech of an HMM into a hybrid algorithm, the performance of the original HMM-based speech recognition algorithm can be improved. The proposed hybrid algorithm is especially effective in cases when the training data are not adequate to characterize the test data. Preliminary results showed that this system gave a word accuracy of 98.5% on the whole TI test set, even when only HMM was used to segment speech utterances into words and states

Keywords

Markov processes; data compression; speech analysis and processing; speech recognition; HMM/LVQ segmentation; TI test set; connected word recognition algorithm; hidden Markov model; hybrid algorithm; learning vector quantisation; speech classification; speech utterances segmentation; temporal variations; test data; training data; word accuracy; Artificial neural networks; Databases; Hidden Markov models; Pattern recognition; Power system modeling; Speech recognition; System testing; Training data; Vector quantization; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on

Conference_Location

Toronto, Ont.

ISSN

1520-6149

Print_ISBN

0-7803-0003-3

Type

conf

DOI

10.1109/ICASSP.1991.150291

Filename

150291