mlsanityData to 14 Oct 2026

Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation

arXiv 2505.16911 ↗First posted 22 May 2025eess.AS cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce a new paradigm for active sound modification: Active Speech Enhancement (ASE). While Active Noise Cancellation (ANC) algorithms focus on suppressing external interference, ASE goes further by actively shaping the speech signal -- both attenuating unwanted noise components and amplifying speech-relevant frequencies -- to improve intelligibility and perceptual quality. To enable this, we propose a novel Transformer-Mamba-based architecture, along with a task-specific loss function designed to jointly optimize interference suppression and signal enrichment. Our method outperforms existing baselines across multiple speech processing tasks -- including denoising, dereverberation, and declipping -- demonstrating the effectiveness of active, targeted modulation in challenging acoustic environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 133 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

52 of 133 references.

References · 52

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  5. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
  6. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
  7. 2022High Fidelity Neural Audio Compressioncited by 687
  8. 2024Jamba: A Hybrid Transformer-Mamba Language Modelcited by 401
  9. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 197
  10. 2020Real Time Speech Enhancement in the Waveform Domaincited by 186
  11. 2020Attention is All You Need in Speech Separationcited by 185
  12. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 182
38 more
  1. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 166
  2. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 141
  3. 2022Conditional Diffusion Probabilistic Model for Speech Enhancementcited by 132
  4. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
  5. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 105
  6. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  7. 2022Speech Enhancement with Score-Based Generative Models in the Complex STFT Domaincited by 102
  8. 2024An Investigation of Incorporating Mamba for Speech Enhancementcited by 62
  9. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 60
  10. 2024Open-Source Conversational AI with SpeechBrain 1.0cited by 56
  11. 2023MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectracited by 52
  12. 2017A Wavenet for Speech Denoisingcited by 47
  13. 2022CMGAN: Conformer-based Metric GAN for Speech Enhancementcited by 45
  14. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separationcited by 45
  15. 2022VoiceFixer: A Unified Framework for High-Fidelity Speech Restorationcited by 37
  16. 2024SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Modelcited by 37
  17. 2024Audio Mamba: Bidirectional State Space Model for Audio Representation Learningcited by 37
  18. 2021TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domaincited by 36
  19. 2024Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakerscited by 28
  20. 2024RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detectioncited by 27
  21. 2024Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesiscited by 23
  22. 2024Audio Mamba: Selective State Spaces for Self-Supervised Audio Representationscited by 19
  23. 2024Rethinking Mamba in Speech Processing by Self-Supervised Modelscited by 11
  24. 2022Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudescited by 10
  25. 2024Audio Mamba: Pretrained Audio State Space Model For Audio Taggingcited by 10
  26. 2024Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super Resolutioncited by 9
  27. 2021Self-attending RNN for Speech Enhancement to Improve Cross-corpus Generalizationcited by 8
  28. 2022A Hybrid SFANC-FxNLMS Algorithm for Active Noise Control based on Deep Learningcited by 7
  29. 2023Diffusion-based speech enhancement with a weighted generative-supervised learning losscited by 7
  30. 2024SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimationcited by 6
  31. 2024GAN-Based Speech Enhancement for Low SNR Using Latent Feature Conditioningcited by 6
  32. 2025DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformerscited by 6
  33. 2023Deep Generative Fixed-filter Active Noise Controlcited by 5
  34. 2024TF-Mamba: A Time-Frequency Network for Sound Source Localizationcited by 5
  35. 2022Spatially Selective Active Noise Control Systemscited by 4
  36. 2022Cross-Attention is all you need: Real-Time Streaming Transformers for Personalised Speech Enhancementcited by 3
  37. 2024Unsupervised learning based end-to-end delayless generative fixed-filter active noise controlcited by 3
  38. 2024An Exploration of Length Generalization in Transformer-Based Speech Enhancementcited by 2

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training
  2. 2023NADiffuSE: Noise-aware Diffusion-based Model for Speech Enhancement
  3. 2024Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement
  4. 2026TokenSE: a Mamba-based discrete token speech enhancement framework for cochlear implants
  5. 2025Model as Loss: A Self-Consistent Training Paradigm
  6. 2024GALD-SE: Guided Anisotropic Lightweight Diffusion for Efficient Speech Enhancement
  7. 2025Universal Speech Enhancement with Regression and Generative Mamba
  8. 2025Schr"odinger Bridge Mamba for One-Step Speech Enhancement