oboVox 远场扬声器识别：使用预训练模型的新型数据增强方法

arXiv - EE - Audio and Speech Processing Pub Date : 2024-09-16 DOI:arxiv-2409.10240

Muhammad Sudipto Siam Dip, Md Anik Hasan, Sapnil Sarker Bipro, Md Abdur Raiyan, Mohammod Abdul Motin

{"title":"oboVox 远场扬声器识别：使用预训练模型的新型数据增强方法","authors":"Muhammad Sudipto Siam Dip, Md Anik Hasan, Sapnil Sarker Bipro, Md Abdur Raiyan, Mohammod Abdul Motin","doi":"arxiv-2409.10240","DOIUrl":null,"url":null,"abstract":"In this study, we address the challenge of speaker recognition using a novel\ndata augmentation technique of adding noise to enrollment files. This technique\nefficiently aligns the sources of test and enrollment files, enhancing\ncomparability. Various pre-trained models were employed, with the resnet model\nachieving the highest DCF of 0.84 and an EER of 13.44. The augmentation\ntechnique notably improved these results to 0.75 DCF and 12.79 EER for the\nresnet model. Comparative analysis revealed the superiority of resnet over\nmodels such as ECPA, Mel-spectrogram, Payonnet, and Titanet large. Results,\nalong with different augmentation schemes, contribute to the success of RoboVox\nfar-field speaker recognition in this paper","PeriodicalId":501284,"journal":{"name":"arXiv - EE - Audio and Speech Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"oboVox Far Field Speaker Recognition: A Novel Data Augmentation Approach with Pretrained Models\",\"authors\":\"Muhammad Sudipto Siam Dip, Md Anik Hasan, Sapnil Sarker Bipro, Md Abdur Raiyan, Mohammod Abdul Motin\",\"doi\":\"arxiv-2409.10240\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this study, we address the challenge of speaker recognition using a novel\\ndata augmentation technique of adding noise to enrollment files. This technique\\nefficiently aligns the sources of test and enrollment files, enhancing\\ncomparability. Various pre-trained models were employed, with the resnet model\\nachieving the highest DCF of 0.84 and an EER of 13.44. The augmentation\\ntechnique notably improved these results to 0.75 DCF and 12.79 EER for the\\nresnet model. Comparative analysis revealed the superiority of resnet over\\nmodels such as ECPA, Mel-spectrogram, Payonnet, and Titanet large. Results,\\nalong with different augmentation schemes, contribute to the success of RoboVox\\nfar-field speaker recognition in this paper\",\"PeriodicalId\":501284,\"journal\":{\"name\":\"arXiv - EE - Audio and Speech Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Audio and Speech Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.10240\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Audio and Speech Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.10240","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

在这项研究中，我们采用了一种新的数据增强技术，即在注册文件中添加噪音，来应对说话人识别的挑战。这项技术有效地调整了测试文件和注册文件的来源，提高了可比性。我们采用了多种预训练模型，其中 resnet 模型的 DCF 最高，为 0.84，EER 为 13.44。增强技术显著改善了这些结果，resnet 模型的 DCF 和 EER 分别为 0.75 和 12.79。对比分析表明，resnet 优于 ECPA、Mel-spectrogram、Payonnet 和 Titanet large 等模型。这些结果以及不同的增强方案为本文中 RoboVox 远场扬声器识别的成功做出了贡献。

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

微信好友朋友圈 QQ好友复制链接

本刊更多论文

oboVox Far Field Speaker Recognition: A Novel Data Augmentation Approach with Pretrained Models

In this study, we address the challenge of speaker recognition using a novel data augmentation technique of adding noise to enrollment files. This technique efficiently aligns the sources of test and enrollment files, enhancing comparability. Various pre-trained models were employed, with the resnet model achieving the highest DCF of 0.84 and an EER of 13.44. The augmentation technique notably improved these results to 0.75 DCF and 12.79 EER for the resnet model. Comparative analysis revealed the superiority of resnet over models such as ECPA, Mel-spectrogram, Payonnet, and Titanet large. Results, along with different augmentation schemes, contribute to the success of RoboVox far-field speaker recognition in this paper

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

arXiv - EE - Audio and Speech Processing

自引率

0.00%

发文量