EUROSPEECH 2001 Scandinavia
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.
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.