Correcting errors in speech recognition with articulatory dynamics

Authors:
Frank Rudzicz
Affiliations:
University of Toronto, Toronto, Ontario, Canada
Venue:
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Year:
2010

Citing 5
Cited 2

Learning Dynamic Bayesian Networks

Adaptive Processing of Sequences and Data Structures, International Summer School on Neural Networks, "E.R. Caianiello"-Tutorial Lectures
Data-driven production models for speech processing

Data-driven production models for speech processing
Control System Design: An Introduction to State-Space Methods (Dover Books on Engineering)

Control System Design: An Introduction to State-Space Methods (Dover Books on Engineering)
Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model

Speech Communication
Applying discretized articulatory knowledge to dysarthric speech

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing

Using articulatory likelihoods in the recognition of dysarthric speech

Speech Communication
Dysarthric speech recognition error correction using weighted finite state transducers based on context---dependent pronunciation variation

ICCHP'12 Proceedings of the 13th international conference on Computers Helping People with Special Needs - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a novel mechanism for incorporating articulatory dynamics into speech recognition with the theory of task dynamics. This system reranks sentence-level hypotheses by the likelihoods of their hypothetical articulatory realizations which are derived from relationships learned with aligned acoustic/articulatory data. Experiments compare this with two baseline systems, namely an acoustic hidden Markov model and a dynamic Bayes network augmented with discretized representations of the vocal tract. Our system based on task dynamics reduces word-error rates significantly by 10.2% relative to the best baseline models.