Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue

arXiv:2609.03321 · cs.CL · Submitted 2026-09-03 · Read on arXiv

cs.CL

Submitted: 2026-09-03

Updated: 2026-09-03

Code: https://github.com/Liyht/def-fsm

Terminology

• Ablation — 10× in this paper · explained in 1 episode
• F1 Score — 7× in this paper · explained in 3 episodes
• Ablation study — 6× in this paper · explained in 1 episode
• Foundation Model — 4× in this paper · explained in 3 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Core — 3× in this paper · explained in 2 episodes
• Decoupling — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• Source-Aware Calibrated — 3× in this paper
• Decode — 2× in this paper · explained in 2 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Alternation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Floor-Taking Interruption — 1× in this paper
• For the Machine-interrupts-User — 1× in this paper
• For the User-interrupts-Machine — 1× in this paper
• Foundation Models — 1× in this paper · explained in 7 episodes
• Full-duplex interaction — 1× in this paper · explained in 2 episodes
• Inter-Pausal Unit — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Lexical Diversity — 1× in this paper · explained in 2 episodes
• Modality Gap — 1× in this paper · explained in 4 episodes
• Neural Finite State Machine — 1× in this paper
• Robustness — 1× in this paper · explained in 5 episodes
• Self-Supervised Learning — 1× in this paper · explained in 7 episodes
• Semantic Gap — 1× in this paper · explained in 2 episodes
• State Management — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• MinMo: A Multimodal Large Language Model for Seamless Voice Interaction
• VoiceBench: Benchmarking LLM-Based Voice Assistants
• From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models
• Moshi: a speech-text foundation model for real-time dialogue
• FlexDuo: A Pluggable System for Enabling Full-Duplex Capabilities in Speech Dialogue Systems
• Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Models
• WavChat: A Survey of Spoken Dialogue Models
• Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
• Adaptive Turn-Taking for Real-time Multi-Party Voice Agents
• GPT-4 Technical Report
• Robust Speech Recognition via Large-Scale Weak Supervision
• Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering