mlsanityData to 13 Oct 2026

DuplexChat: Constructing Speaker-Separated Full-Duplex Dialogue Speech at Scale for Spoken Dialogue Language Modeling

arXiv 2607.04941 ↗First posted 6 Jul 2026cs.CL cs.SD eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Full-duplex spoken dialogue models are trained on conversational speech in which each speaker is represented as a separate stream, but existing large-scale public speech corpora are mostly monaural, making them unsuited for SDLM training. We present DuplexChat, an open-source corpus for full-duplex spoken dialogue models, and DuplexChat-Pipe, a pipeline for constructing speaker-separated full-duplex dialogue speech from public podcast feeds. DuplexChat-Pipe filters language-specific podcast feeds, retrieves and cleans episode audio, extracts diarization-guided two-speaker dialogue clips, and applies speech separation and restoration to produce one channel per speaker. Running this pipeline yields a speaker-separated spoken dialogue corpus covering 282,634 hours of English and 132,723 hours of Japanese. Analysis results on DuplexChat show that it contains turn-taking dynamics present in human dialogues.

Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Builds on 13 of its 22 references that are in the map. First posted on arXiv 6 Jul 2026.

Builds on

13 of 22 references.

References · 13

  1. 2020Scaling Laws for Neural Language Modelscited by 6,494
  2. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 550
  3. 2023SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilitiescited by 523
  4. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 393
  5. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 239
  6. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 202
  7. 2024Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLMcited by 137
  8. 2022Generative Spoken Dialogue Language Modelingcited by 126
  9. 2023TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudiocited by 59
  10. 2026PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Modelscited by 59
  11. 2024YODAS: Youtube-Oriented Dataset for Audio and Speechcited by 56
  12. 2026DialogueSidon: Recovering Full-Duplex Dialogue Tracks from In-the-Wild Dialogue Audiocited by 4
1 more
  1. 2024J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modelingcited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026ConversationalVoice: Full-Duplex Speech Data from Real Conversations through Source-Faithful Reconstruction and Conversation-Grounded Expansioncited by 1
  2. 2026Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized Guidancecited by 0
  3. 2026Evaluating Real-Time Voice Agents: From Component Quality to Grounded Outcomescited by 0