arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.01677cs.CL
收藏

自监督语音表示在分析语音的同时保持语音特征

Self-Supervised Speech Representations Preserve Speech Characteristics while Anonymizing Voices

Universidad de Antioquia UdeA(安蒂奥基亚大学);Pratech group SAS(普拉泰克集团股份有限公司)

Abner Hernandez, Paula Andrea Pérez-Toro, Juan Camilo Vásquez-Correa, Juan Rafael Orozco-Arroyave, Andreas Maier, Seung Hee Yang

摘要:

收集语音数据是训练语音识别系统和其他基于语音的机器学习模型的重要步骤。然而,隐私保护问题日益受到关注,必须加以解决。目前的研究调查使用的声音转换作为匿名的声音的方法。特别是,我们训练几个语音转换模型,使用自监督语音表示,包括Wav2Vec2.0,Hubert和UniSpeech。转换后的声音保留了低字出错率内的1%的原始声音。在LibriSpeech测试集上,等出错率从1.52%增加到46.24%,在来自VCTK语料库的说话人上,等错误率从3.75%增加到45.84%,这表明说话人验证的性能下降。最后,我们对构音障碍语音数据进行了实验,表明可以从匿名语音中提取与发音、韵律、发声和音韵相关的语音特征,以区分健康语音和病态语音。

英文摘要:

Collecting speech data is an important step in training speech recognition systems and other speech-based machine learning models. However, the issue of privacy protection is an increasing concern that must be addressed. The current study investigates the use of voice conversion as a method for anonymizing voices. In particular, we train several voice conversion models using self-supervised speech representations including Wav2Vec2.0, Hubert and UniSpeech. Converted voices retain a low word error rate within 1% of the original voice. Equal error rate increases from 1.52% to 46.24% on the LibriSpeech test set and from 3.75% to 45.84% on speakers from the VCTK corpus which signifies degraded performance on speaker verification. Lastly, we conduct experiments on dysarthric speech data to show that speech features relevant to articulation, prosody, phonation and phonology can be extracted from anonymized voices for discriminating between healthy and pathological speech.

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。

↑