Performance Evaluation of Convolutive Blind Source Separation of Mixtures of Unequal-Level Speech Signals
Malay Gupta, S.C. Douglas · 2007
The performance of any signal enhancement method depends on the relative amplitudes of the signals and interferences present in the original measurements. Previous evaluations of convolutive blind source separation methods for speech enhancement have considered situations where the signal-to-interference ratios (SIRs) of all the talkers' speech signals are nearly equal in the recorded signal mixtures. This paper presents real-world separation experiments of two- and three-talker signal mixtures in which the level of one talker's speech is lower than those of the others. Methods based on decorrelation, frequency-domain information maximization, and time-domain contrast optimization are studied. Experimental evaluation shows that the weaker talker's speech receives the most enhancement in the separated system's outputs, whereas the stronger talker's speech signals receive moderate to little enhancement beyond a limiting value.