Home

Evaluating Source Separation Algorithms With Reverberant Speech

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

Title:
Evaluating Source Separation Algorithms With Reverberant Speech
Author(s):
Mandel, Michael I.
Bressler, Scott
Shinn-Cunningham, Barbara
Ellis, Daniel P. W.
Date:
Type:
Articles
Department:
Electrical Engineering
Volume:
18
Permanent URL:
Book/Journal Title:
IEEE Transactions on Audio, Speech, and Language Processing
Abstract:
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.
Subject(s):
Electrical engineering
Acoustics
Publisher DOI:
http://dx.doi.org/10.1109/TASL.2010.2052252
Item views:
196
Metadata:
text | xml

In Partnership with the Center for Digital Research and Scholarship at Columbia University Libraries/Information Services | Terms of Use