https://scholars.lib.ntu.edu.tw/handle/123456789/607148
標題: | S2VC: A framework for any-to-any voice conversion with self-supervised pretrained representations | 作者: | Lin J.-H Lin Y.Y Chien C.-M HUNG-YI LEE |
關鍵字: | Any-to-any;Representation learning;Self-supervised learning;Voice conversion;Linguistics;Speech communication;Supervised learning;Content information;Conversion model;Posteriorgram;Source features;Target feature;Target information;Signal encoding | 公開日期: | 2021 | 卷: | 6 | 起(迄)頁: | 4785-4789 | 來源出版物: | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH | 摘要: | Any-to-any voice conversion (VC) aims to convert the timbre of utterances from and to any speakers seen or unseen during training. Various any-to-any VC approaches have been proposed like AUTOVC, AdaINVC, and FragmentVC. AUTOVC, and AdaINVC utilize source and target encoders to disentangle the content and speaker information of the features. FragmentVC utilizes two encoders to encode source and target information and adopts cross attention to align the source and target features with similar phonetic content. Moreover, pretrained features are adopted. AUTOVC used d-vector to extract speaker information, and self-supervised learning (SSL) features like wav2vec 2.0 is used in FragmentVC to extract the phonetic content information. Different from previous works, we proposed S2VC that utilizes Self-Supervised features as both source and target features for the VC model. Supervised phoneme posteriorgram (PPG), which is believed to be speaker-independent and widely used in VC to extract content information, is chosen as a strong baseline for SSL features. The objective evaluation and subjective evaluation both show models taking SSL feature CPC as both source and target features outperforms that taking PPG as source feature, suggesting that SSL features have great potential in improving VC. Copyright ? 2021 ISCA. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85119252798&doi=10.21437%2fInterspeech.2021-1356&partnerID=40&md5=219b3ef905a25cf860f06fbfd54565e4 https://scholars.lib.ntu.edu.tw/handle/123456789/607148 |
ISSN: | 2308457X | DOI: | 10.21437/Interspeech.2021-1356 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。