有无并行数据的语音转换语音特征的稀疏表示

Berrak Sisman, Haizhou Li, K. Tan
{"title":"有无并行数据的语音转换语音特征的稀疏表示","authors":"Berrak Sisman, Haizhou Li, K. Tan","doi":"10.1109/ASRU.2017.8269002","DOIUrl":null,"url":null,"abstract":"This paper presents a voice conversion framework that uses phonetic information in an exemplar-based voice conversion approach. The proposed idea is motivated by the fact that phone-dependent exemplars lead to better estimation of activation matrix, therefore, possibly better conversion. We propose to use the phone segmentation results from automatic speech recognition (ASR) to construct a sub-dictionary for each phone. The proposed framework can work with or without parallel training data. With parallel training data, we found that phonetic sub-dictionary outperforms the state-of-the-art baseline in objective and subjective evaluations. Without parallel training data, we use Phonetic PosteriorGrams (PPGs) as the speaker-independent exemplars in the phonetic sub-dictionary to serve as a bridge between speakers. We report that such technique achieves a competitive performance without the need of parallel training data.","PeriodicalId":290868,"journal":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"13 1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"40","resultStr":"{\"title\":\"Sparse representation of phonetic features for voice conversion with and without parallel data\",\"authors\":\"Berrak Sisman, Haizhou Li, K. Tan\",\"doi\":\"10.1109/ASRU.2017.8269002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a voice conversion framework that uses phonetic information in an exemplar-based voice conversion approach. The proposed idea is motivated by the fact that phone-dependent exemplars lead to better estimation of activation matrix, therefore, possibly better conversion. We propose to use the phone segmentation results from automatic speech recognition (ASR) to construct a sub-dictionary for each phone. The proposed framework can work with or without parallel training data. With parallel training data, we found that phonetic sub-dictionary outperforms the state-of-the-art baseline in objective and subjective evaluations. Without parallel training data, we use Phonetic PosteriorGrams (PPGs) as the speaker-independent exemplars in the phonetic sub-dictionary to serve as a bridge between speakers. We report that such technique achieves a competitive performance without the need of parallel training data.\",\"PeriodicalId\":290868,\"journal\":{\"name\":\"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)\",\"volume\":\"13 1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"40\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ASRU.2017.8269002\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASRU.2017.8269002","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 40

摘要

本文提出了一种基于实例的语音转换方法中使用语音信息的语音转换框架。所提出的想法的动机是,手机依赖的例子导致更好的估计激活矩阵,因此,可能更好的转换。我们建议使用自动语音识别(ASR)的电话分割结果为每个电话构建子字典。所提出的框架可以使用或不使用并行训练数据。通过并行训练数据,我们发现语音子字典在客观和主观评价方面都优于最先进的基线。在没有并行训练数据的情况下,我们使用语音后图(PPGs)作为语音子字典中与说话人无关的样本,作为说话人之间的桥梁。我们报告说,这种技术在不需要并行训练数据的情况下实现了竞争性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Sparse representation of phonetic features for voice conversion with and without parallel data
This paper presents a voice conversion framework that uses phonetic information in an exemplar-based voice conversion approach. The proposed idea is motivated by the fact that phone-dependent exemplars lead to better estimation of activation matrix, therefore, possibly better conversion. We propose to use the phone segmentation results from automatic speech recognition (ASR) to construct a sub-dictionary for each phone. The proposed framework can work with or without parallel training data. With parallel training data, we found that phonetic sub-dictionary outperforms the state-of-the-art baseline in objective and subjective evaluations. Without parallel training data, we use Phonetic PosteriorGrams (PPGs) as the speaker-independent exemplars in the phonetic sub-dictionary to serve as a bridge between speakers. We report that such technique achieves a competitive performance without the need of parallel training data.
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:604180095
Book学术官方微信