Large vocabulary recognition using linked predictive neural networks

Author

Tebelskis, Joe ; Waibel, Alex

Author_Institution

Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA

fYear

1990

fDate

3-6 Apr 1990

Firstpage

437

Abstract

A large-vocabulary isolated word recognition system based on linked predictive neural networks (LPNNs) is presented. In this system, neural networks are used as predictors of speech frames, enabling a pool of such networks to serve as phoneme models. Higher-level algorithms are used to organize these networks, linking them into sequences corresponding to the phonetic spellings of words, and to train and evaluate the networks for word recognition. By virtue of linking phonemic networks, the LPNN is vocabulary independent and can be applied to large-vocabulary recognition. Recognition rates of 94% for a 234-word Japanese vocabulary of acoustically similar words and 90% for a larger vocabulary of 924 words are obtained

Keywords

neural nets; speech recognition; 234-word Japanese vocabulary; acoustically similar words; large-vocabulary isolated word recognition system; linked predictive neural networks; neural net training; phoneme models; phonetic spellings; vocabulary independent; Computer science; Dynamic programming; Joining processes; Neural networks; Predictive models; Speech; Speech enhancement; Speech processing; Speech recognition; Viterbi algorithm; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115742

Filename

115742