# Self-Listening：让全双工语音模型在打断后锚定真实已播内容

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-04 08:00
- AIHOT 分数：45
- AIHOT 链接：https://aihot.news/items/cmtu5zovr10jurofpni5knjow
- 原文链接：https://arxiv.org/abs/2609.05592

## AI 摘要

全双工语音模型可同时听与说，但其文本生成、语音合成与音频播放异步进行，导致模型自认为已说的内容可能与用户实际听到的不符。为此研究者提出 Self-Listening 方法，将模型实际播放的语音作为输入流回馈给模型，使打断恢复基于用户真实听到的内容；并推出含同质训练与测试划分的 AnchorSpeech 数据集，实验显示该方法相较全双工基线取得更好的锚定表现。

## 正文

Full-duplex spoken language models can listen and speak simultaneously, enabling them to handle interruptions and backchannels in human conversation. However, text generation, speech synthesis, and audio playback proceed asynchronously. As a result, what a model believes it has said may not match what has actually been played to the user. We refer to the problem of recovering from an interruption while remaining aware of the model's realized speech as anchor interruption. To address this problem, we propose Self-Listening, a full-duplex modeling approach that interleaves user speech, model text, and the model's played speech. By feeding the realized speech output back to the model as an input stream, self-listening grounds interruption recovery in what the user has actually heard. We further introduce AnchorSpeech, a collection with homogeneous training and test splits for tracking which items of structured ordered responses have actually been spoken. AnchorSpeech-test evaluates whether a model can respond consistently with the last completed item before an interruption. Experiments show that, compared with full-duplex baselines, models equipped with self-listening mechanism achieve better anchoring performance.