Supervised single-microphone multi-talker speech separation with conditional random fields
Publication in refereed journal

Times Cited
Altmetrics Information

Other information
AbstractWe apply conditional random field (CRF) for single-microphone speech separation in a supervised learning scenario. We train the parameters with mixture data in which the sources are competing with the same average signal power. Compared with factorial hidden Markov model (HMM) baselines, the CRF settings require fewer training mixture data to improve objective speech quality measures and speech recognition accuracy of the reconstructed sources, when mixing ratios of training and testing mixture data are matched. The CRF settings also handle minor mixing ratio mismatch after adjusting the gain factors of the sources with non-linear mappings inspired from the mixture-maximization model. When the mixing ratio mismatch further increases such that the speech mixture is dominated by only one source, factorial HMM finally catches up with and performs better than the CRF settings due to improved model accuracy. We also develop a convex statistical inference simplification based on linear-chain CRFs. The simplification achieves the same performance level as the original CRF settings after integrating additional observations.
All Author(s) ListYeung Y.T., Lee T., Leung C.-C.
Journal nameIEEE Transactions on Audio, Speech and Language Processing
Volume Number23
Issue Number12
PublisherInstitute of Electrical and Electronics Engineers
Place of PublicationUnited States
Pages2334 - 2342
LanguagesEnglish-United Kingdom
KeywordsConditional random fields (CRFs), Single-microphone speech separation, Statistical model-based methods

Last updated on 2021-28-02 at 01:48