SEACrowd/audio_keyword_spotting
收藏数据集概述
数据集名称
Audio Keyword Spotting
语言
印尼语 (ind)
任务类别
语音识别 (Speech Recognition)
数据集版本
- 源版本: 0.0.1
- SEACrowd版本: 2024.06.20
许可证
Creative Commons Attribution 4.0 (cc-by-4.0)
引用
如果使用该数据集，请引用以下文献：
@inproceedings{mazumder2021multilingual,
title={Multilingual Spoken Words Corpus},
author={Mazumder, Mark and Chitlangia, Sharad and Banbury, Colby and Kang, Yiping and Ciro, Juan Manuel and Achorn, Keith and Galvez, Daniel and Sabini, Mark and Mattson, Peter and Kanter, David and others},
booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},
year={2021}
}
@inproceedings{wu-etal-2018-creating,
title = "Creating a Translation Matrix of the {B}ible{}s Names Across 591 Languages",
author = "Wu, Winston and
Vyas, Nidhi and
Yarowsky, David",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Hasida, Koiti and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{e}l{e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu", booktitle = "Proceedings of the Eleventh International Conference on Language Resources and Evaluation ({LREC} 2018)", month = may, year = "2018", address = "Miyazaki, Japan", publisher = "European Language Resources Association (ELRA)", url = "https://aclanthology.org/L18-1263", } @inproceedings{wu-yarowsky-2018-comparative, title = "A Comparative Study of Extremely Low-Resource Transliteration of the World{}s Languages", author = "Wu, Winston and Yarowsky, David", editor = "Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{e}l{e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios and
Tokunaga, Takenobu",
booktitle = "Proceedings of the Eleventh International Conference on Language Resources and Evaluation ({LREC} 2018)",
month = may,
year = "2018",
address = "Miyazaki, Japan",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L18-1150",
}
@article{lovenia2024seacrowd,
title={SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages},
author={Holy Lovenia and Rahmad Mahendra and Salsabil Maulana Akbar and Lester James V. Miranda and Jennifer Santoso and Elyanah Aco and Akhdan Fadhilah and Jonibek Mansurov and Joseph Marvin Imperial and Onno P. Kampman and Joel Ruben Antony Moniz and Muhammad Ravi Shulthan Habibi and Frederikus Hudi and Railey Montalan and Ryan Ignatius and Joanito Agili Lopo and William Nixon and Börje F. Karlsson and James Jaya and Ryandito Diandaru and Yuze Gao and Patrick Amadeus and Bin Wang and Jan Christian Blaise Cruz and Chenxi Whitehouse and Ivan Halim Parmonangan and Maria Khelli and Wenyu Zhang and Lucky Susanto and Reynard Adha Ryanda and Sonny Lazuardi Hermawan and Dan John Velasco and Muhammad Dehan Al Kautsar and Willy Fitra Hendria and Yasmin Moslem and Noah Flynn and Muhammad Farid Adilazuarda and Haochen Li and Johanes Lee and R. Damanhuri and Shuo Sun and Muhammad Reza Qorib and Amirbek Djanibekov and Wei Qi Leong and Quyet V. Do and Niklas Muennighoff and Tanrada Pansuwan and Ilham Firdausi Putra and Yan Xu and Ngee Chia Tai and Ayu Purwarianti and Sebastian Ruder and William Tjhi and Peerat Limkonchotiwat and Alham Fikri Aji and Sedrick Keh and Genta Indra Winata and Ruochen Zhang and Fajri Koto and Zheng-Xin Yong and Samuel Cahyawijaya},
year={2024},
eprint={2406.10118},
journal={arXiv preprint arXiv: 2406.10118}
}
