Target Speaker Extraction

Ask about this topic

Overview

Target speaker extraction separates or enhances a selected person’s speech in mixtures, helping listeners follow conversations and improving downstream speech recognition. Systems condition neural separators or masking networks on enrollment speech, while other approaches use visual identity, microphone-array spatial cues, text, or neural signals; generative flows and autoregressive models offer alternatives to conventional separation. Current work increasingly addresses streaming and real conversations, where overlap, reverberation, noise, changing speakers, and differences between enrollment and target speech challenge models trained on simulated mixtures. A central tension is balancing intelligibility, speaker fidelity, perceptual quality, and latency, while ensuring objective metrics reflect real listening and recognition performance.

Latest papers

CardsList

38 papers11 papers in the last four weeks, up 83% on the four weeks before. 0.1% of all new papers.

  1. The Voice on the Line

    Oct 26, 2026Husein ZolkepliSpeech ProcessingTarget Speaker Extraction

    Scicom (MSC) Berhad, Malaysia

  2. Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

    Oct 23, 2026Wendi Sang, Kai Li, Yifan Li +2Target Speaker ExtractionStreaming Inference

    School of Computer Technology and Application, Qinghai University, Xining 810016, China · Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua Laboratory of Brain and Intelligence (THBI), IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China · Intelligent Computing and Application Laboratory of Qinghai Province, Qinghai University, Xining 810016, China +1

  3. MG-REPA: Multi-Granularity Representation Alignment for Generative Target Speaker Extraction

    Oct 23, 2026Dohwan Kim, Jung-Woo ChoiTarget Speaker ExtractionDiffusion Model Alignment

    School of Electrical Engineering, KAIST, Daejeon, South Korea · Department of AI Systems, KAIST, Daejeon, South Korea

  4. NeuroCodec: EEG-Guided Latent-Domain Generative Model for High-Fidelity Target Speaker Extraction

    Oct 21, 2026Julian Silva, Jaliya Kodithuwakku, Navindu Sirimanna +3Target Speaker ExtractionSpeech Processing

    Department of Electronic and Telecommunication Engineering, University of Moratuwa, Katubedda 10400, Sri Lanka

  5. XingChen-UniFE: A Unified Generative Speech Front-End via Complementary Acoustic-Semantic Modeling

    Oct 21, 2026Kelan Kuang, Qihan Hu, Jian Kang +3Audio-Language ModelsTarget Speaker Extraction

    China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd.

  6. MuseFlow-TSE: Music-Aware Target Speech Extraction via Cross-Source Band-Splitting and Data-to-Data Flow Matching

    Oct 21, 2026Lu Ma, Yongliang Wang, Zhewen Su +1Target Speaker Extraction

    JD.com, Inc., Beijing, China

  7. PromptSep-Speaker: Generative Target Speaker Extraction via Multimodal Prompting and Semantic Alignment

    Oct 16, 2026Yutong Wen, Ke Chen, Prem Seetharaman +5Target Speaker Extraction

    Adobe Research, USA · Massachusetts Institute of Technology, USA

  8. CF-AVSS: A Coarse-to-Fine Audio-Visual Speech Separation Framework with Target-Speaker Refinement and Post-Fusion for Real-World AVSE Challenge

    Oct 15, 2026Longjie Luo, Zhongshu Hou, Yuepeng Li +3Speech EnhancementTarget Speaker Extraction

    Tencent Ethereal Audio Lab, Tencent Corporation, China · University of Electronic Science and Technology of China, China

  9. What Makes Codec Tokens Effective for Target Speaker Extraction? A Semantic-Acoustic Disentanglement Perspective

    Oct 12, 2026Wang Xiang, Bang Zeng, Ming LiTarget Speaker ExtractionDisentangled Representation Learning

    Wuhan University · The Chinese University of Hong Kong, Shenzhen

  10. Phonology-Aware Speaker Extraction Frontend for Audio LLMs

    Oct 9, 2026Yanxiang Chen, Haoyuan Deng, Jinyu Wang +4Target Speaker ExtractionSpeech Processing

    Sun Yat-Sen University, Zhuhai, China · Beijing Normal-Hong Kong Baptist University, Zhuhai, China · Fudan University, Shanghai, China

  11. Multimodal Target Speaker Extraction: Towards Unified Speaker Cues Across Modalities

    Sep 28, 2026Xinyuan Qian, Yanghao Zhou, Ziyang Jiang +10Target Speaker ExtractionMultimodal Fusion

    School of Computer and Communication Engineering, University of Science and Technology Beijing, 100083, China · Department of Computer Science and Technology, Beijing Institute of Technology, China · The Chinese University of Hong Kong, Shenzhen, China +5

  12. RemixIT-TSE: Progressive Synthetic-to-Real Adaptation for Target Speech Extraction via Target-Aware Supervision and Remixing

    Sep 28, 2026Yu Wang, Haixin Guan, Shuang Wei +1Synthetic-to-Real Domain AdaptationTarget Speaker Extraction

    Shanghai Normal University, Shanghai, China · Unisound AI Technology Co., Ltd., Beijing, China

  13. Unified Target-Speaker ASR with Text and Enrollment Speech Cues

    Sep 27, 2026Yuxiang Mei, Yuchen Yan, Dongxing Xu +2Target Speaker ExtractionAutomatic Speech Recognition

    Shanghai Normal University · Baidu · Unisound

  14. Dialogue-Based Streaming Audio-Visual Target Speaker Extraction with Predictive Dialogue Information

    Sep 25, 2026Shuhan Zhang, Wenxuan Wu, Haizhou LiTarget Speaker ExtractionSpeech Processing

    Shenzhen Loop Area Institute, Shenzhen, China · School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China · The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China

  15. Adapting Personalized Speech Enhancement for Low-Latency Audio-Visual Target-Speaker Extraction

    Sep 24, 2026Rayhan Rashed, Senja Filipi, Ross CutlerTarget Speaker ExtractionSpeech Enhancement

    Microsoft · University of Michigan

  16. Exploring a Single Autoregressive LLM for Unified Target Speech Extraction across Synchronous and Asynchronous Cues

    Sep 24, 2026Wenxuan Wu, Shuhan Zhang, Shuai Wang +1Audio-Visual UnderstandingTarget Speaker Extraction

  17. CHiME-9 ECHI: A Machine Learning Challenge for Enhancing Conversations to Address Hearing Impairment

    Sep 22, 2026Robert Sutherland, Thomas Kuebert, Marko Lugger +6Target Speaker ExtractionSpeech Enhancement

    School of Computer Science, University of Sheffield, Sheffield, United Kingdom · WS Audiology, Erlangen, Germany · ORCA Labs, WS Audiology, Lynge, Denmark +3

  18. Challenges of Multi-Speaker Extraction for Real Conversational Speech Enhancement

    Sep 22, 2026Robert Sutherland, Stefan Goetze, Jon BarkerTarget Speaker ExtractionSpeech Processing

    School of Computer Science, University of Sheffield, Sheffield, United Kingdom · South Westphalia University of Applied Sciences, Iserlohn, Germany

  19. From Speech to Interaction: Analyzing Multimodal Systems in Cocktail-Party Scenarios

    Aug 9, 2026Thai-Binh Nguyen, Zhaolin Li, Jan Niehues +1Target Speaker ExtractionAutomatic Speech Recognition

    Karlsruhe Institute of Technology Karlsruhe, Germany · Carnegie Mellon University Pittsburgh, USA

  20. SAGE: Switch-Aware EEG-Guided Soft Gating for Target Speaker Extraction with In-Trial Switching

    Aug 3, 2026Xuefei Wang, Ximin Chen, Yuting Ding +2Target Speaker ExtractionAudio Source Separation

    Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China · School of Biomedical Engineering, Capital Medical University, Beijing, China

  21. SLT 2026 REAL-TSE Challenge: Real-world Target Speaker Extraction from Conversational Recordings

    Jul 16, 2026Shuai Wang, Zihan Qian, Ke Zhang +9Target Speaker ExtractionSpeech Processing

    Nanjing University, China · Chinese University of Hong Kong (Shenzhen), China · Brno University of Technology, Czechia +3

  22. The SonicAGI System for the REAL-TSE Challenge

    Jul 13, 2026Kai Li, Wendi Sang, Jintao Cheng +1Target Speaker ExtractionSpeech Processing

    Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua University, Beijing, China · IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing, China · Chinese Institute for Brain Research (CIBR), Beijing, China

  23. Breaking the Quality--Intelligibility Trade-off in Streaming Target Speaker Extraction via Deep-Feature-Anchored Preference Optimization

    Jul 11, 2026Shuhai Peng, Jinjiang Liu, Hui Lu +5Target Speaker ExtractionSpeech Processing

    Tsinghua University · The Chinese University of Hong Kong · SenseTime

  24. PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction

    Jul 9, 2026Wanyi Ning, Wei Zhou, Yingpeng Li +3Target Speaker ExtractionSpeech Processing

    Yijiahe AI, Nanjing, China · Tianjin University, Tianjin, China · Nanjing University, Nanjing, China

  25. Position-Aware Target Speaker Extraction for Long-Form Multi-Party Conversations: A Diarization-Free Framework for ASR

    Jun 28, 2026Yichi Wang, Junzhe Chen, Wangjin Zhou +1Target Speaker ExtractionSpeech Processing

    Graduate School of Informatics, Kyoto University, Kyoto, Japan

  26. Breaking Shortcut Learning for Cross-Trial EEG-Guided Target Speech Extraction via Two-Stage Training

    Jun 23, 2026Wonchul Shin, Inyong Choi, Kyogu LeeTarget Speaker ExtractionEEG Decoding

    Department of Intelligence and Information, Seoul National University, Republic of Korea · Department of Communication Sciences and Disorders, University of Iowa, United States · Interdisciplinary Program in Artificial Intelligence, Seoul National University, Republic of Korea +1

  27. Audio Spotforming via Post-Filtering Using Cross-Array Non-target Estimates

    Jun 2, 2026Yuto Ishikawa, Li Li, Shogo Seki +1Microphone Array ProcessingTarget Speaker Extraction

    CyberAgent, Inc., Japan · The University of Tokyo, Japan

  28. 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

  29. StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model

    Apr 21, 2026Shuhai Peng, Hui Lu, Jinjiang Liu +8Target Speaker ExtractionSpeech Processing

    Shenzhen International Graduate School, Tsinghua University · The Chinese University of Hong Kong · SenseTime Research

  30. Plug-and-Steer: Decoupling Separation and Selection in Audio-Visual Target Speaker Extraction

    Mar 20, 2026Doyeop Kwak, Suyeon Lee, Joon Son ChungTarget Speaker ExtractionAudio Source Separation

    Korea Advanced Institute of Science and Technology, South Korea