mlsanityData to 19 Oct 2026

SNR-Progressive Model with Harmonic Compensation for Low-SNR Speech Enhancement

arXiv 2406.16317 ↗First posted 24 Jun 2024cs.SD eess.AScited by 2

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

Abstract (arXiv)

Despite significant progress made in the last decade, deep neural network (DNN) based speech enhancement (SE) still faces the challenge of notable degradation in the quality of recovered speech under low signal-to-noise ratio (SNR) conditions. In this letter, we propose an SNR-progressive speech enhancement model with harmonic compensation for low-SNR SE. Reliable pitch estimation is obtained from the intermediate output, which has the benefit of retaining more speech components than the coarse estimate while possessing a significant higher SNR than the input noisy speech. An effective harmonic compensation mechanism is introduced for better harmonic recovery. Extensive ex-periments demonstrate the advantage of our proposed model. A multi-modal speech extraction system based on the proposed backbone model ranks first in the ICASSP 2024 MISP Challenge: https://mispchallenge.github.io/mispchallenge2023/index.html.

Key facts. Cited by 2 papers in the map (data through 19 Oct 2026). Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models. Builds on 18 of its 36 references that are in the map. First posted on arXiv 24 Jun 2024.

Builds on

18 of 36 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model1 Jun
  2. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Models11 Aug
  3. 2022FRCRN: Boosting Feature Representation using Frequency Recurrence for Monaural Speech Enhancement15 Jun
  4. 2022Universal Speech Enhancement with Score-based Diffusion7 Jun
  5. 2022Cleanformer: A multichannel array configuration-invariant neural enhancement frontend for ASR in smart speakers25 Apr
  6. 2022Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain31 Mar
  7. 2022CMGAN: Conformer-based Metric GAN for Speech Enhancement28 Mar

Other references · 11

  1. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 596
  2. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 342
  3. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 284
  4. 2020Real Time Speech Enhancement in the Waveform Domaincited by 282
  5. 2020Attention is All You Need in Speech Separationcited by 236
  6. 2022TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separationcited by 76
  7. 2020ICASSP 2021 Deep Noise Suppression Challengecited by 57
  8. 2020A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speechcited by 53
  9. 2021A Simultaneous Denoising and Dereverberation Framework with Target Decouplingcited by 28
  10. 2022Description and Discussion on DCASE 2022 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Techniquescited by 21
  11. 2020UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Conditioncited by 9

Built on by

Cited by year (2026 to 19 Oct)

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

2 papers.

  1. 2025A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditionscited by 1
  2. 2026A two-step approach for speech enhancement in low-SNR scenarios using cyclostationary beamforming and DNNscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2022PercepNet+: A Phase and SNR Aware PercepNet for Real-Time Speech Enhancement
  2. 2022A two-stage full-band speech enhancement model with effective spectral compression mapping
  3. 2024KS-Net: Multi-band joint speech restoration and enhancement network for 2024 ICASSP SSI Challenge
  4. 2024GAN-Based Speech Enhancement for Low SNR Using Latent Feature Conditioning
  5. 2021A Modulation-Domain Loss for Neural-Network-based Real-time Speech Enhancement
  6. 2022HGCN: Harmonic gated compensation network for speech enhancement
  7. 2022Deep neural network techniques for monaural speech enhancement: state of the art analysis
  8. 2022Parallel Gated Neural Network With Attention Mechanism For Speech Enhancement