PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialogue

arXiv:2608.07631 · cs.SD, cs.AI, cs.MM · Submitted 2026-08-07 · Read on arXiv

Shibo Wang, Zicheng Zhang, Libo Wang, Junfeng Ma

cs.SD, cs.AI, cs.MM

Submitted: 2026-08-07

Updated: 2026-08-11

Code: https://github.com/CodeForZzc/GCM-Bench

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 16× in this paper · explained in 2 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Grounding — 12× in this paper · explained in 3 episodes
• Abstraction — 8× in this paper · explained in 1 episode
• Referent Anchoring Accuracy — 8× in this paper
• Ablation — 6× in this paper · explained in 1 episode
• Generative Context Mis-anchoring — 6× in this paper
• Robustness — 6× in this paper · explained in 6 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Benchmarking — 3× in this paper · explained in 4 episodes
• Decoder — 3× in this paper · explained in 2 episodes
• Evaluation Protocol — 3× in this paper · explained in 2 episodes
• Composition — 1× in this paper · explained in 2 episodes
• Continuous Batching — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Editor — 1× in this paper · explained in 2 episodes
• Evaluation Framework — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 14 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• KV cache — 1× in this paper · explained in 4 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• State Management — 1× in this paper · explained in 3 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Voice Activity Detection — 1× in this paper

Sources

• FireRedChat: A Pluggable, Full-Duplex Voice Interaction System with Cascaded and Semi-Cascaded Implementations
• From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models
• MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
• Moshi: a speech-text foundation model for real-time dialogue
• MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols
• FlexDuo: A Pluggable System for Enabling Full-Duplex Capabilities in Speech Dialogue Systems
• Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency
• Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner
• Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
• FD-Bench: A Full-Duplex Benchmarking Pipeline Designed for Full Duplex Spoken Dialogue Systems
• $\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
• A Full-duplex Speech Dialogue Scheme Based On Large Language Models
• Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
• URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models
• DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization
• Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systems
• LLM-Enhanced Dialogue Management for Full-Duplex Spoken Dialogue Systems

Related papers

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
• Harmonic Representations in Symbolic Music Transformers are Localized and Controllable
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving