基于生成对抗网络的普通话唱腔合成

Yun Zhou, Hongwu Yang, Ziyan Chen, Yajing Yan
{"title":"基于生成对抗网络的普通话唱腔合成","authors":"Yun Zhou, Hongwu Yang, Ziyan Chen, Yajing Yan","doi":"10.1109/ICICSP50920.2020.9232118","DOIUrl":null,"url":null,"abstract":"This paper proposed a method for statistical parametric singing synthesis incorporating GAN (Generative Adversarial Network) that trained acoustic model. In GAN, the acoustic model was trained to minimize the weighted sum of the conventional minimum generation loss and adversarial loss, which was minimizing the distance between the natural and generated samples parameter, thus effectively solved the problem of over-smoothing. In the experimental part, we established a singing voice corpus with 60 songs and divided them that have been recorded and labeled into about 1000 sentences, of which 950 sentences were for training model. Comparing the generated songs of the method proposed in this paper and HMM, through 10 people MOS scores, the score of the former was 3.12 that was better than the latter of 2.81.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Mandarin Singing Synthesis Based on Generative Adversarial Network\",\"authors\":\"Yun Zhou, Hongwu Yang, Ziyan Chen, Yajing Yan\",\"doi\":\"10.1109/ICICSP50920.2020.9232118\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposed a method for statistical parametric singing synthesis incorporating GAN (Generative Adversarial Network) that trained acoustic model. In GAN, the acoustic model was trained to minimize the weighted sum of the conventional minimum generation loss and adversarial loss, which was minimizing the distance between the natural and generated samples parameter, thus effectively solved the problem of over-smoothing. In the experimental part, we established a singing voice corpus with 60 songs and divided them that have been recorded and labeled into about 1000 sentences, of which 950 sentences were for training model. Comparing the generated songs of the method proposed in this paper and HMM, through 10 people MOS scores, the score of the former was 3.12 that was better than the latter of 2.81.\",\"PeriodicalId\":117760,\"journal\":{\"name\":\"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICICSP50920.2020.9232118\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICICSP50920.2020.9232118","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

本文提出了一种结合生成对抗网络(GAN, Generative Adversarial Network)训练声学模型的统计参数歌唱合成方法。在GAN中,声学模型的训练目标是最小化传统最小生成损失和对抗损失的加权和,即最小化自然样本参数与生成样本参数之间的距离,从而有效地解决了过度平滑问题。在实验部分,我们建立了一个包含60首歌曲的歌唱语音语料库,并将已录制并标注的歌曲分成约1000个句子,其中950个句子用于训练模型。将本文提出的方法生成的歌曲与HMM进行对比,通过10人的MOS评分,前者的得分为3.12,优于后者的2.81。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Mandarin Singing Synthesis Based on Generative Adversarial Network
This paper proposed a method for statistical parametric singing synthesis incorporating GAN (Generative Adversarial Network) that trained acoustic model. In GAN, the acoustic model was trained to minimize the weighted sum of the conventional minimum generation loss and adversarial loss, which was minimizing the distance between the natural and generated samples parameter, thus effectively solved the problem of over-smoothing. In the experimental part, we established a singing voice corpus with 60 songs and divided them that have been recorded and labeled into about 1000 sentences, of which 950 sentences were for training model. Comparing the generated songs of the method proposed in this paper and HMM, through 10 people MOS scores, the score of the former was 3.12 that was better than the latter of 2.81.
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信