arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.07977eess.AS
收藏

检测、关注和提取:关键词引导的目标说话人提取

Detect, Attend and Extract: Keyword Guided Target Speaker Extraction

Nanjing University(南京大学);X-LANCE Lab, MoE Key Lab of Artificial Intelligence, School of Computer Science(X-LANCE实验室,人工智能教育部重点实验室,计算机学院);ALTA Institute, Machine Intelligence Lab, Department of Engineering, University of Cambridge(剑桥大学工程系机器智能研究所ALTA研究所);National University of Singapore(新加坡国立大学);Shenzhen Loop Area Institute(深圳河套学院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Shanghai Jiao Tong University(上海交通大学)

Haoyu Li, Yu Xi, Yidi Jiang, Shuai Wang, Kate Knill, Mark Gales, Haizhou Li, Kai Yu

AI总结:

提出DAE-TSE框架,利用关键词作为线索,通过检测-关注-提取范式实现目标说话人提取,无需干净注册语音,性能优于传统系统。

摘要:

目标说话人提取(TSE)旨在从包含多个竞争说话人的混合语音中提取目标说话人的语音。传统的TSE系统主要依赖说话人线索(如预注册语音)来识别和分离目标说话人。然而,在许多实际场景中,无法获得干净的注册语音,限制了现有方法的适用性。本文提出DAE-TSE,一种关键词引导的TSE框架,通过目标说话人发出的特定关键词来指定目标说话人。通过利用关键词(即部分转录)作为线索,我们的方法为基于注册的TSE提供了一种灵活且实用的替代方案。DAE-TSE遵循检测-关注-提取(DAE)范式:首先检测给定关键词的存在,然后根据关键词内容关注相应的说话人,最后提取目标语音。实验结果表明,DAE-TSE优于依赖干净注册语音的标准TSE系统。据我们所知,这是首次在TSE中利用部分转录作为指定目标说话人的线索,为实际场景提供了灵活且实用的解决方案。我们的代码和演示页面现已公开。

英文摘要:

Target speaker extraction (TSE) aims to extract the speech of a target speaker from mixtures containing multiple competing speakers. Conventional TSE systems predominantly rely on speaker cues, such as pre-enrolled speech, to identify and isolate the target speaker. However, in many practical scenarios, clean enrollment utterances are unavailable, limiting the applicability of existing approaches. In this work, we propose DAE-TSE, a keyword-guided TSE framework that specifies the target speaker through distinct keywords they utter. By leveraging keywords (i.e., partial transcriptions) as cues, our approach provides a flexible and practical alternative to enrollment-based TSE. DAE-TSE follows the Detect-Attend-Extract (DAE) paradigm: it first detects the presence of the given keywords, then attends to the corresponding speaker based on the keyword content, and finally extracts the target speech. Experimental results demonstrate that DAE-TSE outperforms standard TSE systems that rely on clean enrollment speech. To the best of our knowledge, this is the first study to utilize partial transcription as a cue for specifying the target speaker in TSE, offering a flexible and practical solution for real-world scenarios. Our code and demo page are now publicly available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑