mlsanityData to 14 Oct 2026

From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models

arXiv 2509.14515 ↗First posted 18 Sep 2025cs.CL cs.SD eess.AScited by 10

Not on the map. Why?

Abstract (arXiv)

True Full-Duplex (TFD) voice communication--enabling simultaneous listening and speaking with natural turn-taking, overlapping speech, and interruptions--represents a critical milestone toward human-like AI interaction. This survey comprehensively reviews Full-Duplex Spoken Language Models (FD-SLMs) in the LLM era. We establish a taxonomy distinguishing Engineered Synchronization (modular architectures) from Learned Synchronization (end-to-end architectures), and unify fragmented evaluation approaches into a framework encompassing Temporal Dynamics, Behavioral Arbitration, Semantic Coherence, and Acoustic Performance. Through comparative analysis of mainstream FD-SLMs, we identify fundamental challenges: synchronous data scarcity, architectural divergence, and evaluation gaps, providing a roadmap for advancing human-AI communication.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 18 Sep 2025.

Builds on

29 of 43 references.

References · 29

  1. 2024GPT-4o System Cardcited by 4,588
  2. 2022High Fidelity Neural Audio Compressioncited by 687
  3. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
  4. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 431
  5. 2025VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interactioncited by 197
  6. 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 153
  7. 2024Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLMcited by 141
  8. 2022Generative Spoken Dialogue Language Modelingcited by 126
  9. 2025On The Landscape of Spoken Language Models: A Comprehensive Surveycited by 118
  10. 2020Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognitioncited by 113
  11. 2024Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilitiescited by 109
  12. 2025Step-Audio 2 Technical Reportcited by 105
17 more
  1. 2025Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilitiescited by 100
  2. 2024WavChat: A Survey of Spoken Dialogue Modelscited by 90
  3. 2024Recent Advances in Speech Language Models: A Surveycited by 87
  4. 2023Zipformer: A faster and better encoder for automatic speech recognitioncited by 80
  5. 2025MinMo: A Multimodal Large Language Model for Seamless Voice Interactioncited by 79
  6. 2024Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agentscited by 72
  7. 2024A Survey on Speech Large Language Models for Understandingcited by 71
  8. 2024Language Model Can Listen While Speakingcited by 63
  9. 2025Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Modelscited by 54
  10. 2025Discrete Audio Tokens: More Than a Survey!cited by 38
  11. 2025SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Modelcited by 34
  12. 2024SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generationcited by 33
  13. 2025NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Predictioncited by 20
  14. 2025FD-Bench: A Full-Duplex Benchmarking Pipeline Designed for Full Duplex Spoken Dialogue Systemscited by 20
  15. 2025Connector-S: A Survey of Connectors in Multi-modal Large Language Modelscited by 7
  16. 2023Semantic VAD: Low-Latency Voice Activity Detection for Speech Interactioncited by 6
  17. 2025Towards a Japanese Full-duplex Spoken Dialogue Systemcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 10.

10 papers.

  1. 2026Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Modelscited by 7
  2. 2026F-Actor: Controllable Conversational Behaviour in Full-Duplex Modelscited by 3
  3. 2026M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Modelscited by 3
  4. 2026Synchronization and Turn-Taking in Full-Duplex Speech Dialogue Modelscited by 2
  5. 2026Wan-Streamer v0.2: Higher Resolution, Same Latencycited by 2
  6. 2026Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systemscited by 1
  7. 2026PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialoguecited by 0
  8. 2026Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialoguecited by 0
  9. 2026TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Seriescited by 0
  10. 2026RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Cancited by 0