Title | ||
---|---|---|
Distortion-Controlled Training For End-To-End Reverberant Speech Separation With Auxiliary Autoencoding Loss |
Abstract | ||
---|---|---|
The performance of speech enhancement and separation systems in anechoic environments has been significantly advanced with the recent progress in end-to-end neural network architectures. However, the performance of such systems in reverberant environments is yet to be explored. A core problem in reverberant speech separation is about the training and evaluation metrics. Standard timedomain metrics may introduce unexpected distortions during training and fail to properly evaluate the separation performance due to the presence of the reverberations. In this paper, we first introduce the "equal-valued contour" problem in reverberant separation where multiple outputs can lead to the same performance measured by the common metrics. We then investigate how "better" outputs with lower target-specific distortions can be selected by auxiliary autoencoding training (A2T). A2T assumes that the separation is done by a linear operation on the mixture signal, and it adds an loss term on the autoencoding of the direct-path target signals to ensure that the distortion introduced on the direct-path signals is controlled during separation. Evaluations on separation signal quality and speech recognition accuracy show that A2T is able to control the distortion on the direct-path signals and improve the recognition accuracy. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/SLT48900.2021.9383494 | 2021 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP (SLT) |
Keywords | DocType | ISSN |
End-to-end speech separation, reverberant speech separation, auxiliary autoencoding loss | Conference | 2639-5479 |
Citations | PageRank | References |
1 | 0.37 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yi Luo | 1 | 120 | 13.05 |
Cong Han | 2 | 7 | 4.56 |
Nima Mesgarani | 3 | 256 | 22.43 |