Recognition of Convolutive Speech Mixtures by Missing Feature Techniques for ICA
Dorothea Kolossa, Hiroshi Sawada, Ramón Fernández Astudillo, Reinhold Orglmeister, Shoji Makino · 2006
One challenging problem for robust speech recognition is the cocktail party effect, where multiple speaker signals are active simultaneously in an overlapping frequency range. In that case, independent component analysis (ICA) can separate the signals in reverberant environments, also. However, incurred feature distortions prove detrimental for speech recognition. To reduce consequential recognition errors, we describe the use of ICA for the additional estimation of uncertainty information. This information is subsequently used in missing feature speech recognition, which leads to far more correct and accurate recognition also in reverberant situations at RT60= 300ms.