基于频谱声源模型参数的语音身份识别

IF 0.9 4区物理与天体物理 Q4 ACOUSTICS

Acoustical Physics Pub Date : 2024-05-07 DOI:10.1134/s1063771023601462

I. S. Makarov, D. S. Osipov

{"title":"基于频谱声源模型参数的语音身份识别","authors":"I. S. Makarov, D. S. Osipov","doi":"10.1134/s1063771023601462","DOIUrl":null,"url":null,"abstract":"<p>The information content of the parameters of a spectral voice source model in an automatic voice identity recognition problem is studied. For the voice parameters, the identity recognition error was 20.8%; using these parameters together with the pitch period reduced the error to 13.8%. Lastly, the combined use of the spectral model parameters with the pitch period and mel-frequency cepstral coefficients provided the highest accuracy (the recognition error was 1.2%).</p>","PeriodicalId":455,"journal":{"name":"Acoustical Physics","volume":null,"pages":null},"PeriodicalIF":0.9000,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Voice Identity Recognition Based on the Parameters of the Spectral Voice Source Model\",\"authors\":\"I. S. Makarov, D. S. Osipov\",\"doi\":\"10.1134/s1063771023601462\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The information content of the parameters of a spectral voice source model in an automatic voice identity recognition problem is studied. For the voice parameters, the identity recognition error was 20.8%; using these parameters together with the pitch period reduced the error to 13.8%. Lastly, the combined use of the spectral model parameters with the pitch period and mel-frequency cepstral coefficients provided the highest accuracy (the recognition error was 1.2%).</p>\",\"PeriodicalId\":455,\"journal\":{\"name\":\"Acoustical Physics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.9000,\"publicationDate\":\"2024-05-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Acoustical Physics\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1134/s1063771023601462\",\"RegionNum\":4,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ACOUSTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acoustical Physics","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1134/s1063771023601462","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ACOUSTICS","Score":null,"Total":0}

引用次数: 0

摘要

研究了自动语音身份识别问题中频谱声源模型参数的信息含量。在语音参数方面，身份识别误差为 20.8%；将这些参数与音高周期一起使用，误差降低到 13.8%。最后，将频谱模型参数与音高周期和 mel-frequency cepstral coefficients 结合使用的准确率最高（识别误差为 1.2%）。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Voice Identity Recognition Based on the Parameters of the Spectral Voice Source Model

查看原文本刊更多论文

Voice Identity Recognition Based on the Parameters of the Spectral Voice Source Model

The information content of the parameters of a spectral voice source model in an automatic voice identity recognition problem is studied. For the voice parameters, the identity recognition error was 20.8%; using these parameters together with the pitch period reduced the error to 13.8%. Lastly, the combined use of the spectral model parameters with the pitch period and mel-frequency cepstral coefficients provided the highest accuracy (the recognition error was 1.2%).

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

Acoustical Physics 物理-声学

CiteScore

1.60

自引率

50.00%

发文量

审稿时长

3.5 months

期刊介绍： Acoustical Physics is an international peer reviewed journal published with the participation of the Russian Academy of Sciences. It covers theoretical and experimental aspects of basic and applied acoustics: classical problems of linear acoustics and wave theory; nonlinear acoustics; physical acoustics; ocean acoustics and hydroacoustics; atmospheric and aeroacoustics; acoustics of structurally inhomogeneous solids; geological acoustics; acoustical ecology, noise and vibration; chamber acoustics, musical acoustics; acoustic signals processing, computer simulations; acoustics of living systems, biomedical acoustics; physical principles of engineering acoustics. The journal publishes critical reviews, original articles, short communications, and letters to the editor. It covers theoretical and experimental aspects of basic and applied acoustics. The journal welcomes manuscripts from all countries in the English or Russian language.