An LLM Is All You Need: Data-Efficient Adaptation to Full-Duplex, Word-Level Spoken Dialogue
cs.CL, cs.SD, eess.AS
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- High Fidelity Neural Audio Compression
- Moshi: a speech-text foundation model for real-time dialogue
- Voice Activity Projection: Self-supervised Learning of Turn-taking Events
- InteractionBench: Measuring Timing, Task Accuracy, Whisper and Volume, and Grounding in Real-Time Voice Systems
- LoRA: Low-Rank Adaptation of Large Language Models
- Autoregressive Image Generation using Residual Quantization
- Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Models
- Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
- PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems
- Generative Spoken Dialogue Language Modeling
- PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models
- Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents
- Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
- Qwen2.5-Omni Technical Report
- Qwen3-Omni Technical Report
- OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation
- Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data