Advances in confidence measures for large vocabulary

Author

Wendemuth, A. ; Rose, G. ; Dolfing, J.G.A.

Author_Institution

Philips Res. Lab., Aachen, Germany

Volume

2

fYear

1999

fDate

15-19 Mar 1999

Firstpage

705

Abstract

This paper addresses the correct choice and combination of confidence measures in large vocabulary speech recognition tasks. We classify single words within continuous as well as large vocabulary utterances into two categories: utterances within the vocabulary which are recognized correctly, and other utterances, namely misrecognized utterances or (less frequent) out-of-vocabulary (OOV). To this end, we investigate the classification error rate (CER) of several classes of confidence measures and transformations. In particular, we employed data-independent and data-dependent measures. The transformations we investigated include mapping to single confidence measures and linear combinations of these measures. These combinations are computed by means of neural networks trained with Bayes-optimal, and with Gardner-Derrida-optimal criteria. Compared to a recognition system without confidence measures, the selection of (various combinations of) confidence measures, the selection of suitable neural network architectures and training methods, continuously improves the CER

Keywords

Bayes methods; hidden Markov models; neural net architecture; optimisation; signal classification; speech recognition; Bayes-optimal criteria; Gardner-Derrida-optimal criteria; HMM; classification error rate; confidence measures; data-dependent measure; data-independent measure; large vocabulary speech recognition; large vocabulary utterances; linear combinations; misrecognized utterances; neural network architectures; out-of-vocabulary utterances; training methods; transformations; Computer architecture; Computer networks; Error analysis; Hidden Markov models; Laboratories; Neural networks; Particle measurements; Speech recognition; Vectors; 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.1999.759764

Filename

759764