基于矢量量化的单次语音转换

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2020-05-01 DOI:10.1109/ICASSP40776.2020.9053854

Da-Yi Wu, Hung-yi Lee

{"title":"基于矢量量化的单次语音转换","authors":"Da-Yi Wu, Hung-yi Lee","doi":"10.1109/ICASSP40776.2020.9053854","DOIUrl":null,"url":null,"abstract":"In this paper, we propose a vector quantization (VQ) based one-shot voice conversion (VC) approach without any supervision on speaker label. We model the content embedding as a series of discrete codes and take the difference between quantize-before and quantize-after vector as the speaker embedding. We show that this approach has a strong ability to disentangle the content and speaker information with reconstruction loss only, and one-shot VC is thus achieved.","PeriodicalId":13127,"journal":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"38 1","pages":"7734-7738"},"PeriodicalIF":0.0000,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"64","resultStr":"{\"title\":\"One-Shot Voice Conversion by Vector Quantization\",\"authors\":\"Da-Yi Wu, Hung-yi Lee\",\"doi\":\"10.1109/ICASSP40776.2020.9053854\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we propose a vector quantization (VQ) based one-shot voice conversion (VC) approach without any supervision on speaker label. We model the content embedding as a series of discrete codes and take the difference between quantize-before and quantize-after vector as the speaker embedding. We show that this approach has a strong ability to disentangle the content and speaker information with reconstruction loss only, and one-shot VC is thus achieved.\",\"PeriodicalId\":13127,\"journal\":{\"name\":\"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)\",\"volume\":\"38 1\",\"pages\":\"7734-7738\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"64\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICASSP40776.2020.9053854\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP40776.2020.9053854","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 64

摘要

本文提出了一种基于矢量量化(VQ)的单次语音转换(VC)方法，该方法无需对说话人标签进行任何监督。我们将内容嵌入建模为一系列离散码，并将量化前向量和量化后向量的差值作为说话人嵌入。我们的研究表明，该方法具有较强的分离内容和说话人信息的能力，并且只有重建损失，从而实现了一次VC。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

One-Shot Voice Conversion by Vector Quantization

In this paper, we propose a vector quantization (VQ) based one-shot voice conversion (VC) approach without any supervision on speaker label. We model the content embedding as a series of discrete codes and take the difference between quantize-before and quantize-after vector as the speaker embedding. We show that this approach has a strong ability to disentangle the content and speaker information with reconstruction loss only, and one-shot VC is thus achieved.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

自引率

0.00%

发文量