mlsanityData to 19 Oct 2026

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

arXiv 2104.01923 ↗First posted 5 Apr 2021eess.SP cs.SD eess.AScited by 0

On the map: Speech and audio language models → Speech enhancement and noise suppression

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models. Builds on 11 of its 21 references that are in the map. First posted on arXiv 5 Apr 2021.

Builds on

11 of 21 references.

References · 11

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,832
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,659
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,653
  4. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,902
  5. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 342
  6. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 153
  7. 2019QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutionscited by 118
  8. 2019Phase-aware Speech Enhancement with Deep Complex U-Netcited by 110
  9. 2018Improved Speech Enhancement with the Wave-U-Netcited by 41
  10. 2020Channel-Attention Dense U-Net for Multichannel Speech Enhancementcited by 36
  11. 2018Speech Dereverberation Using Fully Convolutional Networkscited by 21

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026U-PAST: A Phase-Aware Audio Spectrogram Transformer-U-Net for Single-Channel Speech Enhancement
  2. 2024Decoupled Spatial and Temporal Processing for Resource Efficient Multichannel Speech Enhancement
  3. 2024Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers
  4. 2022FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement
  5. 2025UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search
  6. 2021Inter-channel Conv-TasNet for multichannel speech enhancement
  7. 2026Latency-Configurable Streaming Speech Enhancement via Asymmetric Temporal Padding
  8. 2023Single-Channel Speech Enhancement with Deep Complex U-Networks and Probabilistic Latent Space Models