An SVM based classification approach to speech separation

Monaural speech separation is a very challenging task. CASAbased systems utilize acoustic features to produce a time-frequency (T-F) mask. In this study, we propose a classification approach to monaural separation problem. Our feature set consists of pitchbased features and amplitude modulation spectrum features, which can discriminate both voiced and unvoiced speech from nonspeech interference. We employ support vector machines (SVMs) followed by a re-thresholding method to classify each T-F unit as either targetdominated or interference-dominated. An auditory segmentation stage is then utilized to improve SVM-generated results. Systematic evaluations show that our approach produces high quality binary masks and outperforms a previous system in terms of classification accuracy.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Kun Han, DeLiang Wang
• Keywords: Auditory Segmentation Stage, ICASSP 2011, Monaural Separation Problem, Quality Binary Masks, Signal Processing