Litcius/Paper detail

Monaural Speech Dereverberation Using Temporal Convolutional Networks With Self Attention

Yan Zhao, DeLiang Wang, Buye Xu, Tao Zhang

2020IEEE/ACM Transactions on Audio Speech and Language Processing97 citationsDOIOpen Access PDF

Abstract

In daily listening environments, human speech is often degraded by room reverberation, especially under highly reverberant conditions. Such degradation poses a challenge for many speech processing systems, where the performance becomes much worse than in anechoic environments. To combat the effect of reverberation, we propose a monaural (single-channel) speech dereverberation algorithm using temporal convolutional networks with self attention. Specifically, the proposed system includes a self-attention module to produce dynamic representations given input features, a temporal convolutional network to learn a nonlinear mapping from such representations to the magnitude spectrum of anechoic speech, and a one-dimensional (1-D) convolution module to smooth the enhanced magnitude among adjacent frames. Systematic evaluations demonstrate that the proposed algorithm improves objective metrics of speech quality in a wide range of reverberant conditions. In addition, it generalizes well to untrained reverberation times, room sizes, measured room impulse responses, real-world recorded noisy-reverberant speech, and different speakers.

Topics & Concepts

ReverberationMonauralSpeech recognitionComputer scienceImpulse responseAnechoic chamberConvolution (computer science)Impulse (physics)Speech enhancementActive listeningSpeech processingAcousticsBackground noiseArtificial intelligenceMathematicsTelecommunicationsArtificial neural networkPsychologyCommunicationPhysicsQuantum mechanicsMathematical analysisSpeech and Audio ProcessingAdvanced Adaptive Filtering TechniquesHearing Loss and Rehabilitation