On the optimality of ideal binary time-frequency masks
Speech Communication
ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
DSP'09 Proceedings of the 16th international conference on Digital Signal Processing
A two microphone-based approach for source localization of multiple speech sources
IEEE Transactions on Audio, Speech, and Language Processing
A tandem algorithm for pitch estimation and voiced speech segregation
IEEE Transactions on Audio, Speech, and Language Processing
Hi-index | 0.00 |
The problem of single-channel speaker separation attempts to extract a speech signal uttered by the speaker of interest from a signal containing a mixture of acoustic signals. Most algorithms that deal with this problem are based on masking, wherein unreliable frequency components from the mixed signal spectrogram are suppressed, and the reliable components are inverted to obtain the speech signal from speaker of interest. Most current techniques estimate this mask in a binary fashion, resulting in a hard mask. In this paper, we present two techniques to separate out the speech signal of the speaker of interest from a mixture of speech signals. One technique estimates all the spectral components of the desired speaker. The second technique estimates a soft mask that weights the frequency subbands of the mixed signal. In both cases, the speech signal of the speaker of interest is reconstructed from the complete spectral descriptions obtained. In their native form, these algorithms are computationally expensive. We also present fast factored approximations to the algorithms. Experiments reveal that the proposed algorithms can result in significant enhancement of individual speakers in mixed recordings, consistently achieving better performance than that obtained with hard binary masks.