Speech Enhancement

Follow this topic Ask about this topic

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

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

Multi-Channel Speech Enhancement for Cocktail Party Speech Emotion Recognition
Feb 21, 2026Youjun Chen, Guinan Li, Mengzhe Geng +9Speech Emotion Recognition Multimodal Emotion Recognition
The Chinese University of Hong Kong, Hong Kong SAR, China · National Research Council Canada, Canada · Institute of Software, Chinese Academy of Sciences, China
Lend me an Ear: Speech Enhancement Using a Robotic Arm with a Microphone Array
Feb 19, 2026Zachary Turcotte, François GrondinSpeech Enhancement Microphone Array Processing
Department of Electrical and Computer Engineering, Université de Sherbrooke, Québec, Canada
Loud-loss: A Perceptually Motivated Loss Function for Speech Enhancement Based on Equal-Loudness Contours
Nov 8, 2025Zixuan Li, Xueliang Zhang, Changjiang Zhao +5Speech Enhancement Perceptual Loss
College of Computer Science, Inner Mongolia University, China · Lenovo, China
UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement
Oct 23, 2025Haoyin Yan, Chengwei Liu, Shaofei Xue +4Target Speaker Extraction Decoder-Only Language Models
Qwen Business Unit of Alibaba, China · Tongyi AI Lab of Alibaba, China
Cyclic MPDR Beamforming for Suppression of Almost-Cyclostationary Acoustic Interference
Oct 21, 2025Giovanni Bologni, Martin Bo M\oller, Richard Heusdens +1Speech Enhancement Non-Stationary Time Series
Signal Processing Systems Group, Delft University of Technology, Delft, The Netherlands · Bang & Olufsen, Struer, 7600, Denmark · Netherlands Defence Academy, 1781 AC Den Helder, The Netherlands
Audio-Visual Speech Enhancement: Architectural Design and Deployment Strategies
Aug 11, 2025Anis Hamadouche, Haifeng Luo, Mathini Sellathurai +2Speech Enhancement Edge-Cloud Computing
School of Engineering & Physical Sciences, Heriot-Watt University, Edinburgh EH14 4AS, UK · SDAIA-KFUPM Joint Research Centre for Artificial Intelligence, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia · College of Engineering Department of Electrical and Computer Engineering, San Diego State University, USA
Unified Architecture and Unsupervised Speech Disentanglement for Speaker Embedding-Free Enrollment in Personalized Speech Enhancement
May 18, 2025Ziling Huang, Haixin Guan, Yanhua LongSpeech Enhancement Speaker Disentanglement
Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, 200234, China · SHNU-Unisound Natural Human-Computer Interaction Lab, Shanghai Normal University · Unisound AI Technology Co., Ltd., Beijing, China
Textual Echo Cancellation
Aug 13, 2020Shaojin Ding, Ye Jia, Ke Hu +1Sequence-to-Sequence Models Speech Enhancement
Google LLC, USA

Feb 21, 2026J/K move · Enter open · S save

Multi-Channel Speech Enhancement for Cocktail Party Speech Emotion Recognition

Youjun Chen, Guinan Li, Mengzhe Geng, Xurong Xie+8

The Chinese University of Hong Kong, Hong Kong SAR, China · National Research Council Canada, Canada · Institute of Software, Chinese Academy of Sciences, China

Speech Emotion Recognition Multimodal Emotion Recognition Speech Enhancement

Open paper AskPDF arXiv

This paper highlights the critical importance of multi-channel speech enhancement (MCSE) for speech emotion recognition (ER) in cocktail party scenarios. A multi-channel speech dereverberation and separation front-end integrating DNN-WPE and mask-based MVDR is used to extract the target speaker's speech from the mixture speech, before being fed into the downstream ER back-end using HuBERT- and ViT-based speech and visual features. Experiments on mixture speech constructed using the IEMOCAP and MSP-FACE datasets suggest the MCSE output consistently outperforms domain fine-tuned single-channel speech representations produced by: a) Conformer-based metric GANs; and b) WavLM SSL features with optional SE-ER dual task fine-tuning. Statistically significant increases in weighted, unweighted accuracy and F1 measures by up to 9.5%, 8.5% and 9.1% absolute (17.1%, 14.7% and 16.0% relative) are obtained over the above single-channel baselines. The generalization of IEMOCAP trained MCSE front-ends are also shown when being zero-shot applied to out-of-domain MSP-FACE data.