Single-tree method for grammar-directed search

Author

Nguyen, Long ; Schwartz, Richard

Author_Institution

BBN Technol., GTE Internetworking, Cambridge, MA, USA

Volume

2

fYear

1999

fDate

15-19 Mar 1999

Firstpage

613

Abstract

We present a very fast and accurate fast-match algorithm which, when followed by a regular beam search restricted within only the subset of words selected by the fast-match, can speed up the recognition process by at least two orders of magnitude in comparison to a typical single-pass speech recognizer utilizing the Viterbi (or beam) search algorithm. In this search strategy, the recognition vocabulary is structured as a single phonetic tree in the fast-match pass. The search on this phonetic tree is a variation of the Viterbi algorithm. Especially, we are able to use a word bigram language model without making copies of the tree during the search. This is a novel fast-match algorithm that has two important properties: high-accuracy recognition and run-time proportional to only the cube root of the vocabulary size

Keywords

acoustic signal processing; grammars; pattern matching; probability; speech recognition; tree searching; Viterbi algorithm; Viterbi search algorithm; accurate fast-match algorithm; acoustic models; beam search; continuous speech recognition; fast-match pass; grammar-directed search; high-accuracy recognition; language bigram probability; phonetic tree; run-time; single-pass speech recognizer; single-tree method; structured recognition vocabulary; vocabulary size; word bigram language model; word recognition; Acoustic beams; Lattices; Runtime; Speech processing; Speech recognition; Technological innovation; Viterbi algorithm; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on

Conference_Location

Phoenix, AZ

ISSN

1520-6149

Print_ISBN

0-7803-5041-3

Type

conf

DOI

10.1109/ICASSP.1999.759741

Filename

759741