| Popis: |
This is thepretrained models and anonymized speaker vectorsfrom two of our papers: "Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models," (Odyssey2022) https://arxiv.org/abs/2202.13097 "Analyzing Language-Independent Speaker Anonymization Framework under Unseen Conditions," (arXiv)https://arxiv.org/abs/2203.14834 The authors areXiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko. This data is meant to be used with our open-source implementation, which can be found here: https://github.com/nii-yamagishilab/SSL-SAS This study is supported by JST CREST Grants (JPMJCR18A6 and JPMJCR20D3), MEXT KAKENHI Grants (21K17775, 21H04906, 21K11951, 18H04112), and the VoicePersonal project (ANR-18-JSTS-0001). More information about the directory structure and how to use the data can be found in the READMEs on GitHub. |
