Convolutive Blind Signal Separation Spatial Effectiveness in Speech Intelligibility Improvement

J. Kociński, A. Sęk and P. Libiszewski Institute of Acoustics, Adam Mickiewicz University, Umultowska 85, 61-614 Poznań, Poland

Full Text PDF

Blind signal separation is one of the latest methods to improve the signal to noise ratio. The main objective of blind source separation is the transformation of mixtures of recorded signals to obtain each source signal at the output of the procedure, assuming that they are statistically independent. For acoustic signals it can be concluded that the correct separation is possible only if the source signals are spatially separated. That finding suggests analogies with the classical spatial filtering (beamforming). In this study we analyzed an effect of the angular separation of two source signals (i.e. speech and babble noise) to improve speech intelligibility. For this purpose, we chose the blind source separation algorithm based on the convolutive separation, based on second order statistics only. As a system of sensors a dummy head was used (one microphone inside each ear canal), which simulated two hearing aids of a hearing impaired person. The speech reception threshold, before and after the blind source separation was determined. The results have shown significant improvement in speech intelligibility after applying blind source separation (speach reception threshold fell even more than a dozen dB) in cases where the source signals were angularly separated. However, in cases where the source signals were coming from the same directions, the improvement was not observed. Moreover, the effectiveness of the blind source separation, to a large extent, depended on the relative positions of signal sources in space.

DOI: 10.12693/APhysPolA.119.996 PACS numbers: 43.72.-p, 43.60.-c, 43.60.+d