https://scholars.lib.ntu.edu.tw/handle/123456789/580908
標題: | How Far Are We from Robust Voice Conversion: A Survey | 作者: | Huang T.-H Lin J.-H Lee H.-Y. HUNG-YI LEE |
關鍵字: | Embeddings; Sampling rates; Speaker identification; Voice conversion; Deep learning | 公開日期: | 2021 | 起(迄)頁: | 514-521 | 來源出版物: | 2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Proceedings | 摘要: | Voice conversion technologies have been greatly improved in recent years with the help of deep learning, but their capabilities of producing natural sounding utterances in different conditions remain unclear. In this paper, we gave a thorough study of the robustness of known VC models. We also modified these models, such as the replacement of speaker embeddings, to further improve their performances. We found that the sampling rate and audio duration greatly influence voice conversion. All the VC models suffer from unseen data, but AdaIN-VC is relatively more robust. Also, the speaker embedding jointly trained is more suitable for voice conversion than those trained on speaker identification. ? 2021 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85103941990&doi=10.1109%2fSLT48900.2021.9383498&partnerID=40&md5=6e894cbd7d659ca5df07d11ff320858a https://scholars.lib.ntu.edu.tw/handle/123456789/580908 |
DOI: | 10.1109/SLT48900.2021.9383498 |
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。