Developments in continuous speech dictation using the ARPA WSJ task

Author

Gauvain, J.-L. ; Lamel, L. ; Adda-Decker, M.

Author_Institution

Lab. d´´Informatique pour la Mecanique et les Sci. de l´´Ingenieur, CNRS, Orsay, France

Volume

1

fYear

1995

fDate

9-12 May 1995

Firstpage

65

Abstract

We report on our recent development work in large vocabulary, American English continuous speech dictation. We have experimented with (1) alternative analyses for the acoustic front end, (2) the use of an enlarged vocabulary so as to reduce the number of errors due to out-of-vocabulary words, (3) extensions to the lexical representation, (4) the use of additional acoustic training data, and (5) modification of the acoustic models for telephone speech. The recognizer was evaluated on Hubs 1 and 2 of the fall 1994 ARPA NAB CSR Hub and Spoke Benchmark test. Experimental results for development and evaluation test data are given, as well as an analysis of the errors on the development data

Keywords

acoustic signal processing; dictation; speech processing; speech recognition; telephony; ARPA NAB CSR Hub and Spoke Benchmark test; ARPA WSJ task; American English continuous speech dictation; Wall Street Journal; acoustic front end; acoustic models; acoustic training data; continuous speech dictation; development test data; enlarged vocabulary; error analysis; evaluation test data; experimental results; large vocabulary speech dictation; lexical representation; out-of-vocabulary words; speech recognition; telephone speech; Acoustic testing; Benchmark testing; Context modeling; Hidden Markov models; Microphones; Speech analysis; Statistics; Telephony; Training data; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.479274

Filename

479274