mlsanityData to 14 Oct 2026

FD-Bench: A Full-Duplex Benchmarking Pipeline Designed for Full Duplex Spoken Dialogue Systems

arXiv 2507.19040 ↗First posted 25 Jul 2025eess.AS cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

Full-duplex spoken dialogue systems (FDSDS) enable more natural human-machine interactions by allowing real-time user interruptions and backchanneling, compared to traditional SDS that rely on turn-taking. However, existing benchmarks lack metrics for FD scenes, e.g., evaluating model performance during user interruptions. In this paper, we present a comprehensive FD benchmarking pipeline utilizing LLMs, TTS, and ASR to address this gap. It assesses FDSDS's ability to handle user interruptions, manage delays, and maintain robustness in challenging scenarios with diverse novel metrics. We applied our benchmark to three open-source FDSDS (Moshi, Freeze-omni, and VITA-1.5) using over 40 hours of generated speech, with 293 simulated conversations and 1,200 interruptions. The results show that all models continue to face challenges, such as failing to respond to user interruptions, under frequent disruptions and noisy conditions. Demonstrations, data, and code will be released.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

22 of 30 references.

References · 22

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2023Qwen Technical Reportcited by 3,344
  4. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
  5. 2023SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilitiescited by 529
  6. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  7. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  8. 2023WhisperX: Time-Accurate Speech Transcription of Long-Form Audiocited by 326
  9. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 288
  10. 2023AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Headcited by 265
  11. 2024GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbotcited by 224
  12. 2024Mini-Omni: Language Models Can Hear, Talk While Thinking in Streamingcited by 210
10 more
  1. 2024VoiceBench: Benchmarking LLM-Based Voice Assistantscited by 200
  2. 2024VITA: Towards Open-Source Interactive Omni Multimodal LLMcited by 173
  3. 2024Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLMcited by 141
  4. 2025MinMo: A Multimodal Large Language Model for Seamless Voice Interactioncited by 79
  5. 2024Language Model Can Listen While Speakingcited by 63
  6. 2024OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversationcited by 60
  7. 2024SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Trainingcited by 59
  8. 2024A Full-duplex Speech Dialogue Scheme Based On Large Language Modelscited by 40
  9. 2024Building a Taiwanese Mandarin Spoken Language Model: A First Attemptcited by 23
  10. 2024Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Modelcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 18.

20 papers.

Sort:

By area:

  1. 2025Game-Time: Evaluating Temporal Dynamics in Spoken Language Modelscited by 13
  2. 2025From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Modelscited by 10
  3. 2026EchoChain: A Full-Duplex Benchmark for State-Update Reasoning Under Interruptionscited by 5
  4. 2026Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMscited by 5
  5. 2026Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steeringcited by 4
  6. 2026Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Modelscited by 3
  7. 2026M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Modelscited by 3
  8. 2026Synchronization and Turn-Taking in Full-Duplex Speech Dialogue Modelscited by 2
  9. 2026VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agentscited by 1
  10. 2026Agentic-DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speechcited by 1
  11. 2026DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agentscited by 1
  12. 2026Full-Duplex Speech Models Take the Floor When Asked, Not When Neededcited by 1
8 more
  1. 2026MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversationcited by 1
  2. 2026Fast When, Careful Who: Dual-Process Multiparty Turn-Taking with Diffusion Augmentationcited by 0
  3. 2026Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agentscited by 0
  4. 2026Neither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Modelscited by 0
  5. 2026APEX-Voice: Can Voice Agents Complete Professional Workflows Through Full-Duplex Interactioncited by 0
  6. 2026DuplexAct-Bench: Broadening Full-Duplex Speech Evaluation toward Proactive Interaction across Diverse Behavioral Requirementscited by 0
  7. 2026Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Modelscited by 0
  8. 2026DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?cited by 0