基于自回归模型的非并行语音转换系统

Kadria Ezzine, M. Frikha, J. Di Martino
{"title":"基于自回归模型的非并行语音转换系统","authors":"Kadria Ezzine, M. Frikha, J. Di Martino","doi":"10.1109/IC_ASET53395.2022.9765886","DOIUrl":null,"url":null,"abstract":"Much existing voice conversion (VC) systems are attractive owing to their high performance in terms of voice quality and speaker similarity. Nevertheless, without parallel training data, some generated waveform trajectories are not yet smooth, leading to degraded sound quality and mispronunciation issues in the converted speech. To address these shortcomings, this paper proposes a non-parallel VC system based on an auto-regressive model, Phonetic PosteriorGrams (PPGs), and an LPCnet vocoder to generate high-quality converted speech. The proposed auto-regressive structure makes our system able to produce the next step outputs from the previous step acoustic features. Further, the use of PPGs aims to convert any unknown source speaker into a specific target speaker due to their speaker-independent properties. We evaluate the effectiveness of our system by performing any-to-one conversion pairs between native English speakers. Objective and subjective measures show that our method outperforms the best non-parallel VC method of Voice Conversion Challenge 2018 in terms of naturalness and speaker similarity.","PeriodicalId":6874,"journal":{"name":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","volume":"61 1","pages":"500-504"},"PeriodicalIF":0.0000,"publicationDate":"2022-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Non-Parallel Voice Conversion System Using An Auto-Regressive Model\",\"authors\":\"Kadria Ezzine, M. Frikha, J. Di Martino\",\"doi\":\"10.1109/IC_ASET53395.2022.9765886\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Much existing voice conversion (VC) systems are attractive owing to their high performance in terms of voice quality and speaker similarity. Nevertheless, without parallel training data, some generated waveform trajectories are not yet smooth, leading to degraded sound quality and mispronunciation issues in the converted speech. To address these shortcomings, this paper proposes a non-parallel VC system based on an auto-regressive model, Phonetic PosteriorGrams (PPGs), and an LPCnet vocoder to generate high-quality converted speech. The proposed auto-regressive structure makes our system able to produce the next step outputs from the previous step acoustic features. Further, the use of PPGs aims to convert any unknown source speaker into a specific target speaker due to their speaker-independent properties. We evaluate the effectiveness of our system by performing any-to-one conversion pairs between native English speakers. Objective and subjective measures show that our method outperforms the best non-parallel VC method of Voice Conversion Challenge 2018 in terms of naturalness and speaker similarity.\",\"PeriodicalId\":6874,\"journal\":{\"name\":\"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)\",\"volume\":\"61 1\",\"pages\":\"500-504\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-03-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IC_ASET53395.2022.9765886\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 5th International Conference on Advanced Systems and Emergent Technologies (IC_ASET)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IC_ASET53395.2022.9765886","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

许多现有的语音转换系统由于其在语音质量和说话者相似度方面的高性能而具有吸引力。然而,在没有并行训练数据的情况下,一些生成的波形轨迹还不光滑,导致转换后的语音出现音质下降和发音错误的问题。为了解决这些缺点,本文提出了一种基于自回归模型、语音后置图(PPGs)和LPCnet声码器的非并行VC系统,以生成高质量的转换语音。所提出的自回归结构使我们的系统能够从前一步声学特征中产生下一步输出。此外,使用ppg的目的是将任何未知的源说话者转换为特定的目标说话者,因为它们与说话者无关。我们通过在英语母语者之间进行任意对一的转换对来评估我们系统的有效性。客观和主观测量表明,我们的方法在自然度和说话人相似度方面优于2018年语音转换挑战赛的最佳非并行VC方法。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Non-Parallel Voice Conversion System Using An Auto-Regressive Model
Much existing voice conversion (VC) systems are attractive owing to their high performance in terms of voice quality and speaker similarity. Nevertheless, without parallel training data, some generated waveform trajectories are not yet smooth, leading to degraded sound quality and mispronunciation issues in the converted speech. To address these shortcomings, this paper proposes a non-parallel VC system based on an auto-regressive model, Phonetic PosteriorGrams (PPGs), and an LPCnet vocoder to generate high-quality converted speech. The proposed auto-regressive structure makes our system able to produce the next step outputs from the previous step acoustic features. Further, the use of PPGs aims to convert any unknown source speaker into a specific target speaker due to their speaker-independent properties. We evaluate the effectiveness of our system by performing any-to-one conversion pairs between native English speakers. Objective and subjective measures show that our method outperforms the best non-parallel VC method of Voice Conversion Challenge 2018 in terms of naturalness and speaker similarity.
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
期刊最新文献
Glioma segmentation based on deep CNN Mechanical Design and Control of an Arm with Two Degrees of Freedom for Inspection and Cleaning Operations Adaptive-Cost Shortest Path Based Heuristic for Space Division Multiplexing Networks Wind Farm Based DFIG Supervision In Case Of Power Gradient Constraint Sun Sensor Design for Full Field of View Coverage
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1