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 time-domain 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 autoenc

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyluo2020distortion

Related papers

• End-to-end Dereverberation, Beamforming, And Speech Recognition With Improved Numerical Stability And Advanced Frontend (2021)10.97
• Unpaired Speech Enhancement By Acoustic And Adversarial Supervision For Speech Recognition (2018)10.21
• Audio-visual Speech Separation And Dereverberation With A Two-stage Multimodal Network (2019)12.47
• End-to-end Source Separation With Adaptive Front-ends (2017)12.17
• Bridging The Gap Between Monaural Speech Enhancement And Recognition With Distortion-independent Acoustic Modeling (2019)7.50
• Rethinking Processing Distortions: Disentangling The Impact Of Speech Enhancement Errors On Speech Recognition Performance (2024)8.35
• Monaural Source Separation: From Anechoic To Reverberant Environments (2021)10.61
• Convolutive Transfer Function Invariant SDR Training Criteria For Multi-channel Reverberant Speech Separation (2020)0.00