EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology

Aalborg, Denmark
September 3-7, 2001


Robust ASR Based On Clean Speech Models: An Evaluation of Missing Data Techniques For Connected Digit Recognition in Noise

Jon Barker, Martin Cooke, Phil Green

Sheffield University, UK

In this study, techniques for classification with missing or unreliable data are applied to the problem of noise-robustness in Automatic Speech Recognition (ASR). The techniques described make minimal assumptions about any noise background and rely instead on what is known about clean speech. A system is evaluated using the Aurora 2 connected digit recognition task. Using models trained on clean speech we obtain a 65% relative improvement over the Aurora clean training baseline system, a performance comparable with the Aurora baseline for multicondition training.

Full Paper

Bibliographic reference.  Barker, Jon / Cooke, Martin / Green, Phil (2001): "Robust ASR based on clean speech models: an evaluation of missing data techniques for connected digit recognition in noise", In EUROSPEECH-2001, 213-217.