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

Aalborg, Denmark
September 3-7, 2001


Feature Extraction and Model-Based Noise Compensation for Noisy Speech Recognition evaluated on AURORA 2 Task

Kaisheng Yao, Jingdong Chen, Kuldip K. Paliwal, Satoshi Nakamura

ATR Spoken Language Translation Research Labs., Japan

We have evaluated several feature-based and a model-based method for robust speech recognition in noise. The evaluation was performed on Aurora 2 task. We show that after a sub-band based spectral subtraction, features can be more robust to additive noise. We also report a robust feature set derived from differential power spectrum (DPS), which is not only robust to additive noise, but also robust to spectrum colorization due to channel effects. When the clean training set is available, we show that a model-based noise compensation method can be effective to improve system robustness to noise. Given the testing sets, as a whole, the feature-based methods can yield about 22% relative improvement in accuracy for multi-condition training task, and the model-based method can have about 63% relative performance improvement when systems were trained on clean training set.

Full Paper

Bibliographic reference.  Yao, Kaisheng / Chen, Jingdong / Paliwal, Kuldip K. / Nakamura, Satoshi (2001): "Feature extraction and model-based noise compensation for noisy speech recognition evaluated on AURORA 2 task", In EUROSPEECH-2001, 233-236.