MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models
Speech-to-speech language models have recently emerged to enhance the naturalness of conversational AI. In particular, full-duplex models are distinguished by their real-time interactivity, including handling of pauses, interruptions, and backchannels. However, improving their factuality remains an open challenge. While scaling the model size could address this gap, it would make real-time inference prohibitively expensive. In this work, we propose MoshiRAG, a modular approach that combines a compact full-duplex interface with selective retrieval to access more powerful knowledge sources. Our asynchronous framework enables the model to identify knowledge-demanding queries and ground its r...
| Authors | Chung-Ming Chien, Manu Orsini, Eugene Kharitonov et al. |
|---|---|
| Primary category | cs.CL |
| Published | 14 April 2026 |
| Last updated at source | 12 May 2026 |
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.