We propose an improved time-domain Blind Source Separation method and apply it to speech signal enhancement using multiple microphone recordings. The improvement consists in utilization of fuzzy clustering instead of a hard one, which is verified by experiments where real-world mixtures of two audio signals are separated from two microphones. Performance of the method is demonstrated by recognizing mixed and separated utterances from the Czech part of the European broadcast news database using our Czech LVCSR system. The separation allows significantly better recognition, e.g., by 32% when the jammer signal is a Gaussian noise and the input signal-to-noise ratio is 10dB.
Bibliographic reference. Malek, Jiri / Koldovsky, Zbynek / Zdansky, Jindrich / Nouza, Jan (2008): "Enhancement of noisy speech recordings via blind source separation", In INTERSPEECH-2008, 159-162.