PulseAugur
EN
LIVE 15:42:19

BayLing-Duplex enables native full-duplex speech dialogue with single LLM

By PulseAugur Editorial · [3 sources] ·

Researchers have developed BayLing-Duplex, a novel full-duplex speech language model that enables simultaneous listening and speaking without relying on external turn-taking modules. This single autoregressive LLM can manage natural conversational phenomena like interruptions and hesitations. Fine-tuned with a modest dataset, BayLing-Duplex demonstrates high success rates in turn-taking and interruption handling, while maintaining or improving response quality compared to turn-based models. AI

IMPACT This research could accelerate the development of more natural and responsive conversational AI agents by enabling true real-time, simultaneous speech interaction.

RANK_REASON The cluster contains an academic paper detailing a new model architecture and experimental results.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

BayLing-Duplex enables native full-duplex speech dialogue with single LLM

COVERAGE [3]

  1. arXiv cs.CL TIER_1 English(EN) · Wenqian Cui, Lei Zhu, Xiaohui Li, Zhihan Guo, Haoli Bai, Lu Hou, Irwin King ·

    TurnGuide: Enhancing Meaningful Full Duplex Spoken Interactions via Dynamic Turn-Level Text-Speech Interleaving

    arXiv:2508.07375v3 Announce Type: replace Abstract: Full-Duplex Speech Language Models (FD-SLMs) are specialized foundation models designed to enable natural, real-time spoken interactions by modeling complex conversational turn-taking such as interruptions, backchannels, and ove…

  2. arXiv cs.CL TIER_1 English(EN) · Qingkai Fang, Shoutao Guo, Yang Feng ·

    BayLing-Duplex: Native Full-Duplex Speech Dialogue with a Single Autoregressive LLM

    arXiv:2606.14528v1 Announce Type: new Abstract: Real-time, full-duplex speech interaction is a key feature of next-generation spoken chatbots, allowing the model to listen and speak at the same time and to handle natural phenomena such as overlap, hesitation, and barge-in. Existi…

  3. arXiv cs.CL TIER_1 English(EN) · Yang Feng ·

    BayLing-Duplex: Native Full-Duplex Speech Dialogue with a Single Autoregressive LLM

    Real-time, full-duplex speech interaction is a key feature of next-generation spoken chatbots, allowing the model to listen and speak at the same time and to handle natural phenomena such as overlap, hesitation, and barge-in. Existing speech language models (SpeechLMs) such as LL…

RELATED ENTITIES

RELATED TOPICS