Error approximation and minimum phone error acoustic model estimation

Authors:
Matthew Gibson;Thomas Hain
Affiliations:
Cambridge University Engineering Department, Cambridge, UK;Department of Computer Science, University of Sheffield, Sheffield, UK
Venue:
IEEE Transactions on Audio, Speech, and Language Processing
Year:
2010

Citing 7
Cited 1

Hidden Markov models, maximum mutual information estimation, and the speech recognition problem

Hidden Markov models, maximum mutual information estimation, and the speech recognition problem
MMIE training of large vocabulary recognition systems

Speech Communication
Overall risk criterion estimation of hidden Markov model parameters

Speech Communication
Broadcast News Transcription Using HTK

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Speaker normalization using efficient frequency warping procedures

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
The development of the AMI system for the transcription of speech in meetings

MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction
The 2005 AMI system for the transcription of speech in meetings

MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction

Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Minimum phone error (MPE) acoustic parameter estimation involves calculation of edit distances (errors) between correct and incorrect hypotheses. In the context of large-vocabulary continuous-speech recognition, this error calculation becomes prohibitively expensive and so errors are approximated. This paper introduces a novel error approximation technique. Analysis shows that this approximation yields a higher correlation to the Levenshtein error metric than a previously used approximation. Experimental evaluations on a large-vocabulary recognition task demonstrate that the novel approximation also delivers significant performance improvements over the previously used approximation when applied to MPE acoustic model estimation.