Context Spanning: A Communication Framework for Full-Duplex Speech Models and External LLM Backends

arXiv:2609.33443 · cs.CL, cs.SD, eess.AS · Submitted 2026-09-27 · Read on arXiv

cs.CL, cs.SD, eess.AS

Submitted: 2026-09-27

Updated: 2026-09-27

Comments: Submit to ICASSP 2027

Code: https://github.com/mindlogic-ai/ContextSpanning

License: http://creativecommons.org/licenses/by/4.0/

The gist: Full-duplex spoken dialogue models can listen and speak simultaneously like the real-time dynamics of human conversation.

Terminology

Abstract

Full-duplex spoken dialogue models can listen and speak simultaneously like the real-time dynamics of human conversation. For natural dialogue, the ability to search for external information in real-time is also an important capability. Many models remain trapped in parametric knowledge, leaving them unable to access real-time information and tool execution. Furthermore, even when Large Language Models (LLM) retrieve information, many duplex speech models process it within a compressed latent space rather than in its raw text form, which can lead to information loss from compression. To address this issue, we propose Context Spanning, a framework for information injection between a full-duplex speech model and an external LLM backend via real-time chunked prefill. The injected frame is encoded in a single forward pass inside the real-time frame budget. It feeds the retrieved information to the speech model as-is, enabling it to reason over the information independently and generate responses. With this approach, our model achieves high performance on Full-Duplex benchmarks and strong results on Question Answering tasks, demonstrating its conversation potential. Context Spanning shows that external information can be injected directly into a duplex speech model, introducing a new simple and powerful mechanism for duplex systems.

Sources

Related papers