8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Large Vocabulary Noise Robustness on Aurora4

Luca Rigazio, Patrick Nguyen, David Kryze, Jean-Claude Junqua

Panasonic Speech Technology Laboratory, USA

This paper presents experiments of noise robust ASR on the Aurora4 database. The database is designed to test large vocabulary systems in presence of noise and channel distortions. A number of different model-based and signal-based noise robustness techniques have been tested. Results show that it is difficult to design a technique that is superior in every condition. Because of this we combined different techniques to improve results. Best results have been obtained when short time compensation / normalization methods are combined with long term environmental adaptation and robust acoustic models. The best average error rate obtained over the 52 conditions is 30.8%. This represents a 40% relative improvement compared to the baseline results [1].

Full Paper

Bibliographic reference.  Rigazio, Luca / Nguyen, Patrick / Kryze, David / Junqua, Jean-Claude (2003): "Large vocabulary noise robustness on Aurora4", In EUROSPEECH-2003, 345-348.