@techreport{oai:ipsj.ixsq.nii.ac.jp:00241662,
 author = {Haopeng, Geng and Daisuke, Saito and Nobuaki, Minematsu and Haopeng, Geng and Daisuke, Saito and Nobuaki, Minematsu},
 issue = {42},
 month = {Dec},
 note = {Evaluating non-native speakers' speech intelligibility is essential in computer-assisted language learning (CALL). Conventional methods, such as using word error rates (WER) from automatic speech recognition (ASR), often lack pedagogical validity due to differences from human speech recognition (HSR). A more effective approach involves native (L1) speakers shadowing non-native (L2) speech, where breakdowns in L1 shadowing indicate unintelligible segments in L2 speech. In this study, we propose a speech generation system that simulates L1 shadowing of L2 speech using seq2seq voice conversion (VC) with latent speech representations. Our experimental results demonstrate that this method effectively replicates the L1 shadowing process, offering a novel tool for evaluating L2 speech intelligibility., Evaluating non-native speakers' speech intelligibility is essential in computer-assisted language learning (CALL). Conventional methods, such as using word error rates (WER) from automatic speech recognition (ASR), often lack pedagogical validity due to differences from human speech recognition (HSR). A more effective approach involves native (L1) speakers shadowing non-native (L2) speech, where breakdowns in L1 shadowing indicate unintelligible segments in L2 speech. In this study, we propose a speech generation system that simulates L1 shadowing of L2 speech using seq2seq voice conversion (VC) with latent speech representations. Our experimental results demonstrate that this method effectively replicates the L1 shadowing process, offering a novel tool for evaluating L2 speech intelligibility.},
 title = {Simulating Native Speaker Shadowing for Non-Native Speech Assessment with Latent Speech Representation},
 year = {2024}
}