Mandel Michael I. author Columbia University. Electrical Engineering Bressler Scott author Shinn-Cunningham Barbara author Ellis Daniel P. W. author Columbia University. Electrical Engineering Columbia University. Electrical Engineering originator text Articles 2010 English 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. Electrical engineering Acoustics 18 7 1872 1883 2010-09 http://dx.doi.org/10.1109/TASL.2010.2052252 http://hdl.handle.net/10022/AC:P:11779 NNC NNC 2011-11-09 14:19:41 -0500 2012-12-18 00:50:59 -0500 5762 eng