Academic Commons

Articles

Evaluating Source Separation Algorithms With Reverberant Speech

Mandel, Michael I.; Bressler, Scott; Shinn-Cunningham, Barbara; Ellis, Daniel P. W.

This paper examines the performance of several source separation systems on a speech separation task for which human intelligibility has previously been measured. For anechoic mixtures, automatic speech recognition (ASR) performance on the separated signals is quite similar to human performance. In reverberation, however, while signal separation has some benefit for ASR, the results are still far below those of human listeners facing the same task. Performing this same experiment with a number of oracle masks created with a priori knowledge of the separated sources motivates a new objective measure of separation performance, the Direct-path, Early echo, and Reverberation, of the Target and Masker (DERTM), which is closely related to the ASR results. This measure indicates that while the non-oracle algorithms successfully reject the direct-path signal from the masking source, they reject less of its reverberation, explaining the disappointing ASR performance.

Files

Also Published In

Title
IEEE Transactions on Audio, Speech, and Language Processing
DOI
https://doi.org/10.1109/TASL.2010.2052252

More About This Work

Academic Units
Electrical Engineering
Published Here
November 9, 2011
Academic Commons provides global access to research and scholarship produced at Columbia University, Barnard College, Teachers College, Union Theological Seminary and Jewish Theological Seminary. Academic Commons is managed by the Columbia University Libraries.