Speech can be represented as a time/frequency distribution of energy using a multi-band filter bank. A Markov random field model, which takes into account the possible time asynch...
This paper presents an improved wavelet-based dereverberation method for automatic speech recognition (ASR). Dereverberation is based on filtering reverberant wavelet coefficients...
In current speech recognition systems mainly Short-Time Fourier Transform based features like MFCC are applied. Dropping the short-time stationarity assumption of the voiced speec...
Model compensation is a standard way of improving the robustness of speech recognition systems to noise. A number of popular schemes are based on vector Taylor series (vts) compen...
The question how to integrate information from different sources in speech decoding is still only partially solved (layered architecture versus integrated search). We investigate t...