Spontaneous speech recognition for the credit card corpus using the HTK toolkit

Author

Young, Stephen J. ; Woodland, Philip C. ; Byrne, W.J.

Author_Institution

Dept. of Eng., Cambridge Univ., UK

Volume

2

Issue

4

fYear

1994

fDate

10/1/1994 12:00:00 AM

Firstpage

615

Lastpage

621

Abstract

This paper describes a speech recognition system for the credit card corpus which was provided as a baseline for the Summer Workshop on Robust Speech Processing held at the Rutgers CAIP Center in July/August 1993. The system was built using a portable HMM toolkit called HTK. This is described, along with details of the training and testing methods used. Benchmark performance results are presented for mixture Gaussian monophones and tied-state triphones using four different language models. The overall accuracy levels achieved were very low, indicating that this is a very difficult recognition task. The paper concludes with a discussion of some specific problems encountered with the Credit Card data and suggestions for future work

Keywords

credit transactions; hidden Markov models; speech recognition; speech recognition equipment; HTK toolkit; benchmark performance results; credit card corpus; language models; mixture Gaussian monophones; portable HMM toolkit; speech recognition system; spontaneous speech recognition; testing method; testing methods; tied-state triphones; training methods; Benchmark testing; Conferences; Credit cards; Databases; Hidden Markov models; Libraries; Robustness; Speech processing; Speech recognition; Vocabulary;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/89.326619

Filename

326619