{
 "id": "aaivu-labs/EmoTa",
 "owner": "aaivu-labs",
 "name": "EmoTa",
 "downloads": 130,
 "likes": 1,
 "last_modified": "2026-07-14T02:37:19.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "emota-academic-commercial-license-v1.0",
 "licence_link": "https://huggingface.co/datasets/aaivu-labs/EmoTa/blob/main/LICENSE.txt",
 "file_licence": "cc-by-nc-4.0",
 "licence_files": [
  "LICENSE.txt"
 ],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "audio-classification"
 ],
 "citation": "@inproceedings{thevakumar-etal-2025-emota,\n    title = \"{E}mo{T}a: A {T}amil Emotional Speech Dataset\",\n    author = \"Thevakumar, Jubeerathan  and\n      Thavarasa, Luxshan  and\n      Sivatheepan, Thanikan  and\n      Kugarajah, Sajeev  and\n      Thayasivam, Uthayasanker\",\n    editor = \"Sarveswaran, Kengatharaiyer  and\n      Vaidya, Ashwini  and\n      Krishna Bal, Bal  and\n      Shams, Sana  and\n      Thapa, Surendrabikram\",\n    booktitle = \"Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)\",\n    month = jan,\n    year = \"2025\",\n    address = \"Abu Dhabi, UAE\",\n    publisher = \"International Committee on Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.chipsal-1.19/\",\n    pages = \"193--201\",\n    abstract = \"This paper introduces EmoTa, the first emotional speech dataset in Tamil, designed to reflect the linguistic diversity of Sri Lankan Tamil speakers. EmoTa comprises 936 recorded utterances from 22 native Tamil speakers (11 male, 11 female), each articulating 19 semantically neutral sentences across five primary emotions: anger, happiness, sadness, fear, and neutrality. To ensure quality, inter-annotator agreement was assessed using Fleiss' Kappa, resulting in a substantial agreement score of 0.74. Initial evaluations using machine learning models, including XGBoost and Random Forest, yielded a high F1-score of 0.91 and 0.90 for emotion classification tasks. By releasing EmoTa, we aim to encourage further expl",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "58682568acd31be03acf07bb33de3f2528e74563",
 "stated_evidence": "https://huggingface.co/datasets/aaivu-labs/EmoTa/blob/58682568acd31be03acf07bb33de3f2528e74563/README.md",
 "file_evidence": "https://huggingface.co/datasets/aaivu-labs/EmoTa/blob/58682568acd31be03acf07bb33de3f2528e74563/LICENSE.txt",
 "card_nc": false
}