• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Working paper

Real-time Streaming Wave-U-Net with Temporal Convolutions for Multichannel Speech Enhancement

In this paper we describe our work that we have done to participate in Task1 of ConferencingSpeech2021 challenge. This task set a goal to develop the solution for multi-channel speech enhancement in a real-time manner. We propose a novel system for streaming speech enhancement. We employ Wave-U-Net architecture with temporal convolutions in encoder and decoder. We incorporate self-attention in decoder to apply attention mask retrieved from skip-connection on features from down-blocks. We explore history cache mechanisms that work like hidden states in recurrent networks and implemented them in proposal solution. It helps us to run inference with chunks length 40 ms and Real-Time Factor 0.4 with the same precision