New strategies for single-channel speech separation (2011)
Abstract / truncated to 115 words
We present new results on single-channel speech separation and suggest a new separation approach to improve the speech quality of separated signals from an observed mix- ture. The key idea is to derive a mixture estimator based on sinusoidal parameters. The proposed estimator is aimed at ﬁnding sinusoidal parameters in the form of codevectors from vector quantization (VQ) codebooks pre-trained for speakers that, when combined, best ﬁt the observed mixed signal. The selected codevectors are then used to reconstruct the recovered signals for the speakers in the mixture. Compared to the log- max mixture estimator used in binary masks and the Wiener ﬁltering approach, it is observed that the proposed method achieves an acceptable perceptual ... toggle 4 keywordssingle-channel source separation – sinusoidal modeling – mixture estimation – speaker identification.
The current layout is optimized for mobile phones. Page previews, thumbnails, and full abstracts will remain hidden until the browser window grows in width.
The current layout is optimized for tablet devices. Page previews and some thumbnails will remain hidden until the browser window grows in width.