Improving automatic speech recognition for lectures through transformation-based rules learned from minimal data

Authors:
Cosmin Munteanu;Gerald Penn;Xiaodan Zhu
Affiliations:
National Research Council Canada, Fredericton, Canada and University of Toronto, Toronto, Canada;University of Toronto, Toronto, Canada;University of Toronto, Toronto, Canada
Venue:
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
Year:
2009

Citing 9
Cited 1

Deterministic part-of-speech tagging with finite-state transducers

Computational Linguistics
Algorithms on strings, trees, and sequences: computer science and computational biology

Algorithms on strings, trees, and sequences: computer science and computational biology
A simple rule-based part of speech tagger

ANLC '92 Proceedings of the third conference on Applied natural language processing
Labeling images with a computer game

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Transformation-based learning in the fast lane

NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
The effect of speech recognition accuracy rates on the usefulness and usability of webcast archives

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Error correction via a post-processor for continuous speech recognition

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Collaborative editing for improved usefulness and usability of transcript-enhanced webcasts

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Style & topic language model adaptation using HMM-LDA

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing

Speech for Content Creation

International Journal of Mobile Human Computer Interaction

Quantified Score

Hi-index	0.00

Visualization

Abstract

We demonstrate that transformation-based learning can be used to correct noisy speech recognition transcripts in the lecture domain with an average word error rate reduction of 12.9%. Our method is distinguished from earlier related work by its robustness to small amounts of training data, and its resulting efficiency, in spite of its use of true word error rate computations as a rule scoring function.