RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can
eess.AS, cs.AI, cs.CL, cs.SD
Submitted: 2026-10-09
Updated: 2026-10-09
Sources
- From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models
- Training Verifiers to Solve Math Word Problems
- Moshi: a speech-text foundation model for real-time dialogue
- Gemma 4 Technical Report
- Qwen3-TTS Technical Report
- DuplexOmni: Real-Time Listening, Seeing, Thinking, and Speaking for Full-Duplex Interaction
- A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State Machine
- PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models
- Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST
- RoFormer: Enhanced Transformer with Rotary Position Embedding
- Qwen2.5-Omni Technical Report
- DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action
- OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation
Related papers
- Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
- X-VC: Zero-shot Streaming Voice Conversion in Codec Space
- Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
- VM-ARRAYDPS: Virtual Microphone Augmented Diffusion Posterior Sampling for Unsupervised Blind Speech Separation
- Conditional Flow Matching for Visually-Guided Acoustic Highlighting
- Anonymization, Not Elimination: Utility-Preserved Speech Anonymization