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 2406.04429eess.AScs.DLcs.MMcs.SD
收藏

InaGVAD:一个具有挑战性的法语电视和广播语料库,标注了语音活动检测和说话人性别分割

InaGVAD : a Challenging French TV and Radio Corpus Annotated for Speech Activity Detection and Speaker Gender Segmentation

French National Institute of Audiovisual (INA)(法国国家视听研究院);Laboratoire de Recherche de l’EPITA (LRE)(EPITA 研究实验室)

David Doukhan, Christine Maertens, William Le Personnic, Ludovic Speroni, Reda Dehak

AI总结:

本文介绍法语视听语料库 InaGVAD,包含 VAD 和说话人性别分割标注,并通过基准测试证明仅用 1 小时多样化数据训练的 X-vector 迁移学习方法即可取得有竞争力的性别分割性能。

摘要:

InaGVAD 是一个从 10 个法语广播频道和 18 个电视频道收集的音频语料库,分为 4 组:综合广播、音乐广播、新闻电视和综合电视。它包含 277 段 1 分钟长的标注录音,旨在代表法语视听节目的声学多样性,并且主要被设计用于构建能够监测媒体中男性和女性说话时间的系统。InaGVAD 提供了语音活动检测(VAD)和说话人性别分割(SGS)标注,并扩展了重叠、说话人特征(性别、年龄、声音质量)以及 10 个非语音事件类别。针对每个频道类别详细说明了标注分布。该数据集被划分为 1 小时的开发子集和 3 小时 37 分钟的测试子集,允许公平且可复现的系统评估。本文提出了一个由 6 个免费可用的 VAD 软件组成的基准,展示了基于频道和非语音事件类别的不同能力。在该语料库上评估了两个现有的 SGS 系统,并与在开发子集上训练的基线 X-vector 迁移学习策略进行了比较。结果表明,我们提出的方法仅在 1 小时(但具有多样性)的数据上训练,就取得了具有竞争力的 SGS 结果。整个 InaGVAD 包,包括语料库、标注、评估脚本和基线训练代码,均可免费获取,促进了该领域未来的发展。

英文摘要:

InaGVAD is an audio corpus collected from 10 French radio and 18 TV channels categorized into 4 groups: generalist radio, music radio, news TV, and generalist TV. It contains 277 1-minute-long annotated recordings aimed at representing the acoustic diversity of French audiovisual programs and was primarily designed to build systems able to monitor men's and women's speaking time in media. inaGVAD is provided with Voice Activity Detection (VAD) and Speaker Gender Segmentation (SGS) annotations extended with overlap, speaker traits (gender, age, voice quality), and 10 non-speech event categories. Annotation distributions are detailed for each channel category. This dataset is partitioned into a 1h development and a 3h37 test subset, allowing fair and reproducible system evaluation. A benchmark of 6 freely available VAD software is presented, showing diverse abilities based on channel and non-speech event categories. Two existing SGS systems are evaluated on the corpus and compared against a baseline X-vector transfer learning strategy, trained on the development subset. Results demonstrate that our proposal, trained on a single - but diverse - hour of data, achieved competitive SGS results. The entire inaGVAD package; including corpus, annotations, evaluation scripts, and baseline training code; is made freely accessible, fostering future advancement in the domain.

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。

↑