cs.LGNov 1, 2026

ReFrame: Silence-Aware Compute Reclamation for Full-Duplex Speech Models

Authors: Zheng Zhou, Guanyi Chen, Jing Wei, Haoyuan Liang, Jian Zhang, Haohuan Fu

Organizations: Tsinghua University · The Hong Kong University of Science and Technology (Guangzhou) · ScaleX-IO · Sun Yat-sen University

Abstract

Full-duplex speech models execute dense model inference for every audio frame throughout a live interaction. This uniform framewise schedule creates sustained GPU load across dialogue states whose computation has strong, reusable temporal structure. ReFrame formulates full-duplex inference as a silence-aware computation problem. Mutual Silence Speculation (MSS) operates when both participants are silent: it evaluates multi-frame Temporal continuations, verifies text and hidden-state stability, and applies batched Mimi audio-token correction. Listening Frame Folding (LFF) operates while the user speaks and the agent listens: it processes already-arrived user frames through parallel Temporal execution and frame-batched audio-token generation while accepting only the verified prefix. Frame-Budget Reinvestment (FBR) assigns the released frame intervals to resumable external retrieval and language-model workers, then injects timely references through Moshi's conditioning interface. We instantiate ReFrame on five full-duplex models spanning Moshi-family, phase-structured, and flattened autoregressive generation. Across the complete 1,225-conversation FDBench, ReFrame reduces measured GPU execution time by 18.80-31.01% and retains 96.92-100% non-PAD text agreement on five different models. On HaluEval tests, FBR increases the number of correct generated spoken answers from 86 to 205 under the same auxiliary-service budget. ReFrame turns recurring dialogue structure into lower inference cost and higher end-to-end service capability.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Why Full-Duplex Speech Models Collapse in Long Conversations

    Oct 23, 2026Yeonju Kim, Bella Godiva, Se Jin Park +1Full-Duplex Spoken Dialogue SystemsLong-Context Modeling

  2. DiffuPlex: Accelerating Full-Duplex Spoken Dialog Models via Rolling Masked Diffusion

    Oct 8, 2026Heeseung KimFull-Duplex Spoken Dialogue SystemsDiffusion Model Inference Acceleration

  3. Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models

    Nov 4, 2026Yutong Bian, Yanglin Zhang, Yuxiang Wang +6Speech Language ModelsSpeculative Decoding