Overview

Speech separation studies how to recover individual speaker streams from mixtures, including recordings with overlap, noise, reverberation, or moving speakers. Common approaches use time- or frequency-domain neural networks, spatial cues from microphone arrays, and target-speaker conditioning; newer generative methods use diffusion, flow matching, or autoregressive audio models. Systems are increasingly evaluated on real conversations and by downstream tasks such as speech recognition and diarization, not only signal-quality scores. Key challenges include generalizing beyond simulated mixtures, keeping speaker identities aligned across long recordings, and balancing quality with streaming latency and computation.

Latest papers

CardsList

38 papers4 papers in the last four weeks, down 20% on the four weeks before. 0.0% of all new papers.

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

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

  2. Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation

    Mar 31, 2026Ui-Hyeop Shin, Hyung-Min ParkSpeech SeparationSpeaker Disentanglement

  3. HRTF-guided Binaural Target Speaker Extraction with Real-World Validation

    Mar 17, 2026Yoav Ellinson, Sharon GannotTarget Speaker ExtractionSpeech Separation

  4. Cepstral Smoothing of Binary Masks for Convolutive Blind Separation of Speech Mixtures

    Mar 16, 2026Ibrahim Missaoui, Zied LachiriSpeech SeparationAudio Source Separation

  5. VorTEX: Various overlap ratio for Target speech EXtraction

    Mar 16, 2026Ro-hoon Oh, Jihwan Seol, Bugeun KimTarget Speaker ExtractionSpeech Separation

  6. RadEar: A Self-Supervised RF Backscatter System for Voice Eavesdropping and Separation

    Mar 12, 2026Qijun Wang, Peihao Yan, Chunqi Qian +1Speech Separation

  7. Moving Speaker Separation via Parallel Spectral-Spatial Processing

    Feb 25, 2026Yuzhu Wang, Archontis Politis, Konstantinos Drossos +1Speech Separation

  8. UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement

    Oct 23, 2025Haoyin Yan, Chengwei Liu, Shaofei Xue +4Target Speaker ExtractionDecoder-Only Language Models