{
 "id": "lbuess/Speech-RATE",
 "owner": "lbuess",
 "name": "Speech-RATE",
 "downloads": 76,
 "likes": 2,
 "last_modified": "2026-05-04T07:45:35.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-to-speech",
  "text-to-audio",
  "audio-classification"
 ],
 "citation": "@inproceedings{buess2026speechct,\n  title={Speechct-clip: Distilling text-image knowledge to speech for voice-native multimodal ct analysis},\n  author={Buess, Lukas and Geier, Jan and Bani-Harouni, David and Pellegrini, Chantal and Keicher, Matthias and Perez-Toro, Paula Andrea and Navab, Nassir and Maier, Andreas and Arias-Vergara, Tomas},\n  booktitle={ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},\n  pages={6286--6290},\n  year={2026},\n  organization={IEEE}\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "576e19b2aa8779f088ac09a74cb04b973e871cad",
 "stated_evidence": "https://huggingface.co/datasets/lbuess/Speech-RATE/blob/576e19b2aa8779f088ac09a74cb04b973e871cad/README.md",
 "file_evidence": "https://huggingface.co/datasets/lbuess/Speech-RATE/tree/576e19b2aa8779f088ac09a74cb04b973e871cad",
 "card_nc": false
}