Relational Data Selection for Data Augmentation of Speaker-Dependent Multi-Band MelGAN Vocoder
Relational Data Selection for Data Augmentation of Speaker-Dependent Multi-Band MelGAN Vocoder
复制标题
DOI：
10.21437/interspeech.2021-806
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Yi-Chiao Wu;Cheng-Hung Hu;Hung-Shin Lee;Yu-Huai Peng;Wen-Chin Huang;Yu Tsao;Hsin-Min Wang;T. Toda
中科院分区：
文献类型：
--
作者：
Yi-Chiao Wu;Cheng-Hung Hu;Hung-Shin Lee;Yu-Huai Peng;Wen-Chin Huang;Yu Tsao;Hsin-Min Wang;T. Toda
如今，神经声码器可以在有大量训练数据的情况下生成非常高保真的语音。虽然说话人相关(SD)声码器的性能通常优于说话人无关(SI)声码器，但对于大多数现实世界的应用来说，收集特定目标说话人的大量数据是不切实际的。针对说话人识别中目标数据有限的问题，提出了一种基于说话人表示和相似性度量的说话人确认数据增强方法。该方法从外部语料库中选择与目标说话人具有相似说话人身份的话语，然后将选择的话语与有限的目标数据相结合进行标清声码器自适应。评估结果表明，与仅使用有限目标数据的声码器相比，使用扩展数据的声码器在合成语音的质量和相似性方面都有所提高。
Nowadays, neural vocoders can generate very high-fidelity speech when a bunch of training data is available. Although a speaker-dependent (SD) vocoder usually outperforms a speaker-independent (SI) vocoder, it is impractical to collect a large amount of data of a specific target speaker for most real-world applications. To tackle the problem of limited target data, a data augmentation method based on speaker representation and similarity measurement of speaker verification is proposed in this paper. The proposed method selects utterances that have similar speaker identity to the target speaker from an external corpus, and then combines the selected utterances with the limited target data for SD vocoder adaptation. The evaluation results show that, compared with the vocoder adapted using only limited target data, the vocoder adapted using augmented data improves both the quality and similarity of synthesized speech.