mlsanityData to 14 Oct 2026

CleanUNet 2: A Hybrid Speech Denoising Model on Waveform and Spectrogram

arXiv 2309.05975 ↗First posted 12 Sep 2023cs.LG cs.SD eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

In this work, we present CleanUNet 2, a speech denoising model that combines the advantages of waveform denoiser and spectrogram denoiser and achieves the best of both worlds. CleanUNet 2 uses a two-stage framework inspired by popular speech synthesis methods that consist of a waveform model and a spectrogram model. Specifically, CleanUNet 2 builds upon CleanUNet, the state-of-the-art waveform denoiser, and further boosts its performance by taking predicted spectrograms from a spectrogram denoiser as the input. We demonstrate that CleanUNet 2 outperforms previous methods in terms of various objective and subjective evaluations.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 46 references that are in the map. First posted on arXiv 12 Sep 2023.

Builds on

25 of 46 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  5. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  6. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 406
  7. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 340
  8. 2020Real Time Speech Enhancement in the Waveform Domaincited by 186
  9. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 166
  10. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 133
  11. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
  12. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
13 more
  1. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  2. 2018ClariNet: Parallel Wave Generation in End-to-End Text-to-Speechcited by 70
  3. 2020FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancementcited by 68
  4. 2019WaveFlow: A Compact Flow-based Model for Raw Audiocited by 51
  5. 2017A Wavenet for Speech Denoisingcited by 47
  6. 2018Speech Denoising with Deep Feature Lossescited by 26
  7. 2021Glance and Gaze: A Collaborative Learning Framework for Single-channel Speech Enhancementcited by 25
  8. 2017Raw Waveform-based Speech Enhancement by Fully Convolutional Networkscited by 24
  9. 2020PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Losscited by 23
  10. 2020Dual-Signal Transformation LSTM Network for Real-Time Noise Suppressioncited by 13
  11. 2022Speech Denoising in the Waveform Domain with Self-Attentioncited by 13
  12. 2020UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Conditioncited by 5
  13. 2017Multi-Objective Learning and Mask-Based Post-Processing for Deep Neural Network Based Speech Enhancementcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Test-Time Training for Speech Enhancementcited by 2
  2. 2026Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancementcited by 0