Speech Enhancement

Ask about this topic

Overview

Speech enhancement seeks to recover clear, intelligible speech from recordings degraded by background noise, reverberation, echo, or other speakers. Methods range from spectral masking and multichannel beamforming, such as MVDR, to neural time-domain models and newer diffusion, flow-matching, and codec-based generators; visual cues and speaker references can help identify the target. Systems are commonly tested on benchmarks such as VoiceBank+DEMAND, DNS, and CHiME, while real-world meetings, hearing aids, and mobile devices bring challenges in domain shift, latency, and power use. A central tension is that better perceptual scores do not always mean more accurate speech recognition, and generative methods must improve quality without changing the speaker’s words or introducing artifacts.

Latest papers

CardsList

128 papers15 papers in the last four weeks, down 50% on the four weeks before. 0.1% of all new papers.

  1. Advancing Electrolaryngeal Speech Enhancement Through Speech-Text Representation Learning

    Jun 1, 2026Ding Ma, Jinyi Mi, Fengji Li +5Representation LearningSpeech Processing

    Graduate School of Informatics, Nagoya University, Nagoya 464-8601, Japan · School of Biological Science and Medical Engineering, Beihang University, Beijing 100191, China · TARVO, Inc., Nagoya 460-0008, Japan +1

  2. IsoNet: Spatially-aware audio-visual target speech extraction in complex acoustic environments

    May 14, 2026Dinanath Padhya, Sajen Maharjan, Binita Adhikari +1Speech EnhancementMultimodal Fusion

    Department of Electronics and Computer Engineering, Thapathali Campus, Institute of Engineering, Tribhuvan University, Kathmandu, Nepal

  3. Exploring Token-Space Manipulation in Latent Audio Tokenizers

    May 11, 2026Francesco Paissan, Luca Della Libera, Mirco Ravanelli +1Audio Representation LearningNeural Audio Codecs

    1Mila – Québec AI Institute · 2Université Laval · 3Concordia University

  4. Predictive-Generative Drift Decomposition for Speech Enhancement and Separation

    May 7, 2026Julius Richter, Yoshiki Masuyama, Christoph Boeddeker +3Stochastic InterpolantsSpeech Processing

    MERL Cambridge, MA, USA

  5. Speech Enhancement Based on Drifting Models

    Apr 27, 2026Liang Xu, Diego Caviedes-Nozal, W. Bastiaan Kleijn +2One-Step Generative ModelingSpeech Enhancement

    Victoria University of Wellington, 3 Lincoln University, New Zealand · GN Advanced Science, Denmark

  6. DialogueSidon: Recovering Full-Duplex Dialogue Tracks from In-the-Wild Dialogue Audio

    Apr 10, 2026Wataru Nakata, Yuki Saito, Kazuki Yamauchi +2Audio Diffusion ModelsSpeech Processing

    The University of Tokyo, Tokyo, Japan · National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan

  7. GAP-URGENet: A Generative-Predictive Fusion Framework for Universal Speech Enhancement

    Apr 2, 2026Xiaobin Rong, Yushi Wang, Zheng Wang +1Speech ProcessingSpeech Enhancement

    Key Laboratory of Modern Acoustics, Nanjing University · NJU-Horizon Intelligent Audio Lab, Horizon Robotics

  8. Real-Time Band-Grouped Vocal Denoising Using Sigmoid-Driven Ideal Ratio Masking

    Mar 31, 2026Daniel WilliamsSpeech Enhancement

    Independent Researcher

  9. A Probabilistic Generative Model for Spectral Speech Enhancement

    Mar 30, 2026Marco Hidalgo-Araya, Raphaël Trésor, Bart Van Erp +3Speech Enhancement

    Department of Electrical Engineering, Eindhoven University of Technology, the Netherlands · Lazy Dynamics B.V., Utrecht, the Netherlands · GN Advanced Science, Eindhoven, the Netherlands

  10. Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers

    Mar 24, 2026Jakob Kienegger, Timo GerkmannBayesian FilteringDirection-of-Arrival Estimation

    Signal Processing Group, Department of Informatics, University of Hamburg, 22527 Hamburg, Germany

  11. LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation

    Mar 23, 2026Kazuki Matsumoto, Ren Uchida, Kohei YatabeSpeech DereverberationLipschitz Neural Networks

    Tokyo University of Agriculture and Technology, Tokyo, Japan

  12. DiT-Flow: Speech Enhancement Robust to Multiple Distortions based on Flow Matching in Latent Space and Diffusion Transformers

    Mar 23, 2026Tianyu Cao, Helin Wang, Ari Frummer +7Speech EnhancementFlow Matching

    Johns Hopkins University · Technion Israel Institute of Technology · University of Haifa

  13. End-to-End Multi-Task Learning for Adjustable Joint Noise Reduction and Hearing Loss Compensation

    Mar 20, 2026Philippe Gonzalez, Vera Margrethe Frederiksen, Torsten Dau +1Speech EnhancementMulti-Task Learning

    The authors are with the Department of Health Technology, Technical University of Denmark, 2800 Lyngby, Denmark.

  14. Investigating the Impact of Speech Enhancement on Audio Deepfake Detection in Noisy Environments

    Mar 16, 2026Anacin, Angela, Shruti Kshirsagar +1Audio Deepfake DetectionSpeech Enhancement

    School of Computing, Wichita State University, Wichita, Kansas, USA · Institut national de la recherche scientifique (INRS–EMT), Montreal, Canada

  15. LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement

    Mar 14, 2026Chih-Ning Chen, Jen-Cheng Hou, Hsin-Min Wang +3LLM-Guided RLSpeech Enhancement

    Department of Electrical Engineering, National Taiwan University, Taiwan · Research Center for Information Technology Innovation, Academia Sinica, Taiwan · Center for Hearing Research, University of California Irvine, USA

  16. Mask2Flow-TSE: Two-Stage Target Speaker Extraction with Masking and Flow Matching

    Mar 13, 2026Junwon Moon, Seungbeom Kim, Hansol Park +4Target Speaker ExtractionFlow Matching

    Sungkyunkwan University · University of Seoul

  17. SEMamba++: A General Speech Restoration Framework Leveraging Global, Local, and Periodic Spectral Patterns

    Mar 12, 2026Yongjoon Lee, Jung-Woo ChoiSpeech EnhancementFrequency-Domain Feature Learning

    Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea

  18. NasoVoce: A Nose-Mounted Low-Audibility Speech Interface for Always-Available Speech Interaction

    Mar 11, 2026Jun Rekimoto, Yu Nishimura, Bojian YangAutomatic Speech RecognitionSpeech Enhancement

    Sony CSL - Kyoto · Sony CSL

  19. StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement

    Mar 10, 2026Xiaobin Rong, Jun Gao, Zheng Wang +3Speech DereverberationSpeech Enhancement

    Key Laboratory of Modern Acoustics, Nanjing University · Collaboration AI, Cisco Systems, Inc. · NJU-Horizon Intelligent Audio Lab, Horizon Robotics

  20. LL-SDR: Low-Latency Speech enhancement through Discrete Representations

    Mar 10, 2026Jingyi Li, Luca Della Libera, Mirco Ravanelli +2Speech EnhancementAudio Tokenization

    Guangdong Institute of Intelligence Science and Technology · Concordia University · Mila – Quebec AI Institute +1

  21. Towards Lightweight Adaptation of Speech Enhancement Models in Real-World Environments

    Mar 8, 2026Longbiao Cheng, Shih-Chii LiuSpeech EnhancementMemory-Efficient Fine-Tuning

    Institute of Neuroinformatics, University of Zurich and ETH Zurich

  22. SLICE: Speech Enhancement via Layer-wise Injection of Conditioning Embeddings

    Mar 5, 2026Seokhoon Moon, Kyudan Jung, Jaegul ChooSpeech EnhancementAudio Diffusion Models

    KAIST · KAIST AI

  23. Visual-Informed Speech Enhancement Using Attention-Based Beamforming

    Mar 5, 2026Chihyun Liu, Jiaxuan Fan, Mingtung Sun +3Speech Enhancement

    Department of Power Mechanical Engineering, National Tsing Hua University, Hsinchu, Taiwan · Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan · Department of Power Mechanical Engineering and Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan +1

  24. Focus Then Listen: An Empirical Study of Plug-and-Play Audio Enhancer for Noise-Robust Large Audio Language Models

    Mar 5, 2026Han Yin, Yang Xiao, Younghoo Kwon +2Audio UnderstandingAudio-Language Models

    School of Electrical Engineering, KAIST, Daejeon, Republic of Korea · University of Melbourne, Australia

  25. When Audio Separation Hurts Zero-Shot ASR: Evaluating SAM-Audio with Whisper on Bengali and English Speech

    Mar 5, 2026Akif Islam, Raufun Nahar, Md. Ekramul HamidASR EvaluationAutomatic Speech Recognition

    Department of Computer Science and Engineering, University of Rajshahi, Rajshahi, Bangladesh · Anan National College of Technology, Tokushima, Japan

  26. An Interpretable, Controllable Time-Varying IIR Denoiser for On-Device Assistive Hearing

    Mar 3, 2026Riccardo Rota, Kiril Ratmanski, Jozef Coldenhoff +1Speech EnhancementOn-Device Inference

    Logitech Europe S.A., Switzerland · EPFL ( ´Ecole Polytechnique F´ed´erale de Lausanne), Switzerland

  27. Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement

    Mar 3, 2026Szu-Wei Fu, Rong Chao, Xuesong Yang +6Speech EnhancementDistortion-Perception Tradeoff

    NVIDIA · Academia Sinica, Taipei, Taiwan

  28. CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Space

    Mar 2, 2026Bowen Zhang, Junchuan Zhao, Ian McLoughlin +2Speech EnhancementNeural Audio Codecs

    Singapore Institute of Technology, Singapore · Nanyang Technological University, Singapore · National University of Singapore, Singapore

  29. mmWave Radar Aware Dual-Conditioned GAN for Speech Reconstruction of Signals With Low SNR

    Feb 25, 2026Jash Karani, Adithya Chittem, Deepan Roy +1Generative Adversarial NetworksSpeech Enhancement

    Department of Electrical and Electronics Engineering, Birla Institute of Technology and Science, Pilani, Rajasthan 333031, India · Department of Computer Science and Information Systems, Birla Institute of Technology and Science, Pilani, Rajasthan 333031, India

  30. Absorbing Discrete Diffusion for Speech Enhancement

    Feb 25, 2026Philippe GonzalezSpeech EnhancementDiffusion Models

    Department of Health Technology, Technical University of Denmark