mlsanityData to 7 Oct 2026

Speech Denoising in the Waveform Domain with Self-Attention

arXiv 2202.07790 ↗First posted 15 Feb 2022cs.SD cs.LG eess.AScited by 13

Not on the map. Why?

Abstract (arXiv)

In this work, we present CleanUNet, a causal speech denoising model on the raw waveform. The proposed model is based on an encoder-decoder architecture combined with several self-attention blocks to refine its bottleneck representations, which is crucial to obtain good results. The model is optimized through a set of losses defined over both waveform and multi-resolution spectrograms. The proposed method outperforms the state-of-the-art models in terms of denoised speech quality from various objective and subjective evaluation metrics. We release our code and models at https://github.com/nvidia/cleanunet.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 21 of its 41 references that are in the map. First posted on arXiv 15 Feb 2022.

Builds on

21 of 41 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  4. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 400
  5. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  6. 2020Real Time Speech Enhancement in the Waveform Domaincited by 183
  7. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 165
  8. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 128
  9. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
  10. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
  11. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  12. 2021U-Net Transformer: Self and Cross Attention for Medical Image Segmentationcited by 81
9 more
  1. 2018ClariNet: Parallel Wave Generation in End-to-End Text-to-Speechcited by 70
  2. 2020FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancementcited by 66
  3. 2017A Wavenet for Speech Denoisingcited by 47
  4. 2018Speech Denoising with Deep Feature Lossescited by 26
  5. 2020PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Losscited by 23
  6. 2020Improving GANs for Speech Enhancementcited by 22
  7. 2020Dual-Signal Transformation LSTM Network for Real-Time Noise Suppressioncited by 11
  8. 2020UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Conditioncited by 5
  9. 2017Multi-Objective Learning and Mask-Based Post-Processing for Deep Neural Network Based Speech Enhancementcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 7; 2025: 1.

13 papers.

Sort:

By area:

  1. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 58
  2. 2023TUNeS: A Temporal U-Net with Self-Attention for Video-based Surgical Phase Recognitioncited by 6
  3. 2024SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Modelcited by 6
  4. 2024RF Challenge: The Data-Driven Radio Frequency Signal Separation Challengecited by 5
  5. 2022JaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpuscited by 4
  6. 2022Deep neural network techniques for monaural speech enhancement: state of the art analysiscited by 3
  7. 2023Complex Image Generation SwinTransformer Network for Audio Denoisingcited by 3
  8. 2023CleanUNet 2: A Hybrid Speech Denoising Model on Waveform and Spectrogramcited by 2
  9. 2024CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruningcited by 2
  10. 2024VCoME: Verbal Video Composition with Multimodal Editing Effectscited by 1
  11. 2024Selective State Space Model for Monaural Speech Enhancementcited by 1
  12. 2025Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deploymentcited by 1
1 more
  1. 2024aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audiocited by 0