Model Releases
D2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex Backbones
arXiv:2610.17124v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) support simultaneous listening and speaking, but often lag behind half-duplex spoken language models (HD-
arXiv:2610.17124v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) support simultaneous listening and speaking, but often lag behind half-duplex spoken language models (HD-SLMs) in general capabilities. We propose Dialogue-to-Duplex (D2), a framework that converts pretrained HD-SLMs into high-capability FD-SLMs at fine temporal granularity. D2 adapts the original audio encoder to streaming through decoder-free representation distillation and learns full-duplex interaction through supervised fine-tuning. We systematically study the effects of chunk size on full-duplex interaction, general capabilities, and inference computation. We apply D2 to two distinct HD-SLM architectures, Qwen3-Omni and LLaMA-Omni 2. At a 12.5Hz update rate, Qwen3-Omni-D2 achieves 99.2% turn-taking success with 521-ms latency, 99.5% interruption success, and a state-of-the-art VoiceBench score of 70.1.
Related
- DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?
- Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering
- MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models
- Neither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Models
Source: arXiv cs.AI | 2026-10-15