{"title":"利用潜在语音表征模拟母语演讲者影子,进行非母语语音评估","authors":"Haopeng Geng, Daisuke Saito, Minematsu Nobuaki","doi":"arxiv-2409.11742","DOIUrl":null,"url":null,"abstract":"Evaluating speech intelligibility is a critical task in computer-aided\nlanguage learning systems. Traditional methods often rely on word error rates\n(WER) provided by automatic speech recognition (ASR) as intelligibility scores.\nHowever, this approach has significant limitations due to notable differences\nbetween human speech recognition (HSR) and ASR. A promising alternative is to\ninvolve a native (L1) speaker in shadowing what nonnative (L2) speakers say.\nBreakdowns or mispronunciations in the L1 speaker's shadowing utterance can\nserve as indicators for assessing L2 speech intelligibility. In this study, we\npropose a speech generation system that simulates the L1 shadowing process\nusing voice conversion (VC) techniques and latent speech representations. Our\nexperimental results demonstrate that this method effectively replicates the L1\nshadowing process, offering an innovative tool to evaluate L2 speech\nintelligibility. Notably, systems that utilize self-supervised speech\nrepresentations (S3R) show a higher degree of similarity to real L1 shadowing\nutterances in both linguistic accuracy and naturalness.","PeriodicalId":501284,"journal":{"name":"arXiv - EE - Audio and Speech Processing","volume":"20 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Simulating Native Speaker Shadowing for Nonnative Speech Assessment with Latent Speech Representations\",\"authors\":\"Haopeng Geng, Daisuke Saito, Minematsu Nobuaki\",\"doi\":\"arxiv-2409.11742\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Evaluating speech intelligibility is a critical task in computer-aided\\nlanguage learning systems. Traditional methods often rely on word error rates\\n(WER) provided by automatic speech recognition (ASR) as intelligibility scores.\\nHowever, this approach has significant limitations due to notable differences\\nbetween human speech recognition (HSR) and ASR. A promising alternative is to\\ninvolve a native (L1) speaker in shadowing what nonnative (L2) speakers say.\\nBreakdowns or mispronunciations in the L1 speaker's shadowing utterance can\\nserve as indicators for assessing L2 speech intelligibility. In this study, we\\npropose a speech generation system that simulates the L1 shadowing process\\nusing voice conversion (VC) techniques and latent speech representations. Our\\nexperimental results demonstrate that this method effectively replicates the L1\\nshadowing process, offering an innovative tool to evaluate L2 speech\\nintelligibility. Notably, systems that utilize self-supervised speech\\nrepresentations (S3R) show a higher degree of similarity to real L1 shadowing\\nutterances in both linguistic accuracy and naturalness.\",\"PeriodicalId\":501284,\"journal\":{\"name\":\"arXiv - EE - Audio and Speech Processing\",\"volume\":\"20 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"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-2409.11742\",\"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-2409.11742","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Simulating Native Speaker Shadowing for Nonnative Speech Assessment with Latent Speech Representations
Evaluating speech intelligibility is a critical task in computer-aided
language learning systems. Traditional methods often rely on word error rates
(WER) provided by automatic speech recognition (ASR) as intelligibility scores.
However, this approach has significant limitations due to notable differences
between human speech recognition (HSR) and ASR. A promising alternative is to
involve a native (L1) speaker in shadowing what nonnative (L2) speakers say.
Breakdowns or mispronunciations in the L1 speaker's shadowing utterance can
serve as indicators for assessing L2 speech intelligibility. In this study, we
propose a speech generation system that simulates the L1 shadowing process
using voice conversion (VC) techniques and latent speech representations. Our
experimental results demonstrate that this method effectively replicates the L1
shadowing process, offering an innovative tool to evaluate L2 speech
intelligibility. Notably, systems that utilize self-supervised speech
representations (S3R) show a higher degree of similarity to real L1 shadowing
utterances in both linguistic accuracy and naturalness.