Syllable-a promising recognition unit for LVCSR

Author

Ganapathiraju, Aravind ; Goel, Vaibhava ; Picone, Joseph ; Corrada, Andres ; Doddington, George ; Kirchhoff, Katrin ; Ordowski, Mark ; Wheatley, Barbara

Author_Institution

Syllable-Based Speech Process. Team, Johns Hopkins Univ., Baltimore, MD, USA

fYear

1997

fDate

14-17 Dec 1997

Firstpage

207

Lastpage

214

Abstract

We present an attempt to model syllable level acoustic information as a viable alternative to the conventional phone level acoustic unit for large vocabulary continuous speech recognition. The motivation for this work were the inherent limitations in the phone based approach, primarily the decompositional nature and lack of larger scale temporal dependencies. We present preliminary but encouraging results on a syllable based recognition system which exceeds the performance of a comparable triphone system both in terms of word error rate (WER) and complexity. The WER of the best syllable system reported here was 49.1% on a standard SWITCHBOARD evaluation

Keywords

acoustic signal processing; speech recognition; word processing; LVCSR; best syllable system; decompositional nature; large vocabulary continuous speech recognition; phone based approach; recognition unit; standard SWITCHBOARD evaluation; syllable based recognition system; syllable level acoustic information modeling; temporal dependencies; triphone system; word error rate; Acoustic applications; Context modeling; Error analysis; Lattices; Natural languages; Speech analysis; Speech processing; Speech recognition; Stability; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Speech Recognition and Understanding, 1997. Proceedings., 1997 IEEE Workshop on

Conference_Location

Santa Barbara, CA

Print_ISBN

0-7803-3698-4

Type

conf

DOI

10.1109/ASRU.1997.659007

Filename

659007