{
 "id": "jspaulsen/esd",
 "owner": "jspaulsen",
 "name": "esd",
 "downloads": 2567,
 "likes": 1,
 "last_modified": "2026-04-01T01:59:37.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "audio-classification",
  "automatic-speech-recognition"
 ],
 "citation": "@inproceedings{zhou2021seen,\n  title={Seen and unseen emotional style transfer for voice conversion with a new emotional speech dataset},\n  author={Zhou, Kun and Sisman, Berrak and Liu, Rui and Li, Haizhou},\n  booktitle={ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},\n  pages={920--924},\n  year={2021},\n  organization={IEEE}\n}\n\n@article{zhou2021emotional,\n  title={Emotional voice conversion: Theory, databases and ESD},\n  journal={Speech Communication},\n  volume={137},\n  pages={1-18},\n  year={2022},\n  issn={0167-6393}\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "dc57273e5872666a110e68dd9e0eee11d5efad60",
 "stated_evidence": "https://huggingface.co/datasets/jspaulsen/esd/blob/dc57273e5872666a110e68dd9e0eee11d5efad60/README.md",
 "file_evidence": "https://huggingface.co/datasets/jspaulsen/esd/tree/dc57273e5872666a110e68dd9e0eee11d5efad60",
 "card_nc": false
}