Speech enhancement and automatic speech recognition (ASR) are most often evaluated in
matched (or multi-condition) settings where the acoustic conditions of the training data …

An adaptive finite impulse response (FIR) filter is a key technique to remove noise in non-
stationary signals. With the rapid development of the various adaptive algorithms, it is both …

Linear discriminant analysis (LDA) is a powerful technique in pattern recognition to reduce
the dimensionality of data vectors. It maximizes discriminability by retaining only those …

Spectrogram factorisation using a dictionary of spectrotemporal atoms has been
successfully employed to separate a mixed audio signal into its source components. When …

In real world speech processing, the signals are often continuous and consist of momentary
segments of speech over non-stationary background noise. It has been demonstrated that …

This paper studies multichannel audio separation using non-negative matrix factorization
(NMF) combined with a new model for spatial covariance matrices (SCM). The proposed …

We consider the task of separating and classifying individual sound sources mixed together.
The main challenge is to achieve robust classification despite residual distortion of the …

Recognition and classification of speech content in everyday environments is challenging
due to the large diversity of realworld noise sources, which may also include competing …

We present our joint contribution to the 2nd CHiME Speech Separation and Recognition
Challenge. Our system combines speech enhancement by supervised sparse non-negative …

Performing automatic speech recognition using exemplars (templates) holds the promise to
provide a better duration and coarticulation modeling compared to conventional approaches …