Loading [a11y]/accessibility-menu.js
A Feature Study for Classification-Based Speech Separation at Low Signal-to-Noise Ratios | IEEE Journals & Magazine | IEEE Xplore

A Feature Study for Classification-Based Speech Separation at Low Signal-to-Noise Ratios


Abstract:

Speech separation can be formulated as a classification problem. In classification-based speech separation, supervised learning is employed to classify time-frequency uni...Show More

Abstract:

Speech separation can be formulated as a classification problem. In classification-based speech separation, supervised learning is employed to classify time-frequency units as either speech-dominant or noise-dominant. In very low signal-to-noise ratio (SNR) conditions, acoustic features extracted from a mixture are crucial for correct classification. In this study, we systematically evaluate a range of promising features for classification-based separation using six nonstationary noises at the low SNR level of -5 dB, which is chosen with the goal of improving human speech intelligibility in mind. In addition, we propose a new feature called multi-resolution cochleagram (MRCG). The new feature is constructed by combining four cochleagrams at different spectrotemporal resolutions in order to capture both the local and contextual information. Experimental results show that MRCG gives the best classification results among all evaluated features. In addition, our results indicate that auto-regressive moving average (ARMA) filtering, a post-processing technique for improving automatic speech recognition features, also improves many acoustic features for speech separation.
Page(s): 1993 - 2002
Date of Publication: 19 September 2014

ISSN Information:


References

References is not available for this document.