Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Handling Convolutional Noise in Missing Data Automatic Speech Recognition

Maarten Van Segbroeck, Hugo Van hamme

Katholieke Universiteit Leuven, Belgium

Missing Data Techniques have already shown their effectiveness in dealing with additive noise in automatic speech recognition systems. For real-life deployments, a compensation for linear filtering distortions is also required. Channel compensation in speech recognition typically involves estimating an additive shift in the log-spectral or cepstral domain. This paper explores a maximum likelihood technique to estimate this model offset while some data are missing. Recognition experiments on the Aurora2 recognition task demonstrate the effectiveness of this technique. In particular, we show that our method is more accurate than previously published methods and can handle narrow-band data.

Full Paper

Bibliographic reference.  Segbroeck, Maarten Van / hamme, Hugo Van (2006): "Handling convolutional noise in missing data automatic speech recognition", In INTERSPEECH-2006, paper 1248-Thu2CaP.11.