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

arXiv:2610.12214 · cs.SD, cs.CL · Submitted 2026-10-08 · Read on arXiv

cs.SD, cs.CL

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/snakers4/silero-vad

Project page: https://diffuplex.github.io

Terminology

• Core — 23× in this paper · explained in 2 episodes
• Benchmark — 20× in this paper · explained in 2 episodes
• Ablation — 14× in this paper · explained in 1 episode
• Transformer — 12× in this paper · explained in 2 episodes
• Full-duplex interaction — 10× in this paper · explained in 2 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Calibration — 5× in this paper · explained in 7 episodes
• Deferral — 5× in this paper · explained in 2 episodes
• Distillation — 5× in this paper · explained in 2 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Speculative Decoding — 5× in this paper · explained in 2 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Block Diffusion — 4× in this paper · explained in 2 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Generative AI — 3× in this paper · explained in 2 episodes
• LoRA Adapters — 3× in this paper · explained in 3 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Automatic Speech Recognition (ASR) — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Hysteresis — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Turn-Over Rate — 1× in this paper
• Unified Framework — 1× in this paper · explained in 5 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset
• Accelerating Large Language Model Decoding with Speculative Sampling
• VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion Modeling
• MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
• Moshi: a speech-text foundation model for real-time dialogue
• Set Block Decoding is a Language Model Inference Accelerator
• ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models
• Raon-Speech Technical Report
• Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction
• Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learning
• FlexDuo: A Pluggable System for Enabling Full-Duplex Capabilities in Speech Dialogue Systems
• Decoupled Weight Decay Regularization
• RelayS2S: A Dual-Path Speculative Generation for Real-Time Dialogue
• DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech
• Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models
• OpenAI GPT-5 System Card
• On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
• Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential
• Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS
• Qwen3-ASR Technical Report

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
• 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
• WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
• Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment