Real-time Streaming Wave-u-net With Temporal Convolutions For Multichannel Speech Enhancement

Abstract

In this paper, we describe the work that we have done to participate in Task1 of the 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 the 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 an inference with chunks length 40ms and Real-Time Factor 0.4 with the same precision.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykuzmin2021real

Related papers

• Improved Speech Enhancement With The Wave-u-net (2018)0.00
• Dilated U-net Based Approach For Multichannel Speech Enhancement From First-order Ambisonics Recordings (2020)0.00
• Multichannel Long-term Streaming Neural Speech Enhancement For Static And Moving Speakers (2024)16.05
• Dynamic Chunk Convolution For Unified Streaming And Non-streaming Conformer ASR (2023)6.77
• Decoupled Spatial And Temporal Processing For Resource Efficient Multichannel Speech Enhancement (2024)0.00
• State-of-the-art Speech Recognition Using Multi-stream Self-attention With Dilated 1D Convolutions (2019)11.93
• Inter-channel Conv-tasnet For Multichannel Speech Enhancement (2021)0.00
• FB-MSTCN: A Full-band Single-channel Speech Enhancement Method Based On Multi-scale Temporal Convolutional Network (2022)6.77