WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words

Lukas Wolf, Klemen Kotar, Greta Tuckute, Eghbal Hosseini, Tamar I. Regev, Ethan Gotlieb Wilcox, Alexander Scott Warstadt


Anthology ID:
2023.conll-babylm.21
Volume:
Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning
Month:
December
Year:
2023
Address:
Singapore
Editors:
Alex Warstadt, Aaron Mueller, Leshem Choshen, Ethan Wilcox, Chengxu Zhuang, Juan Ciro, Rafael Mosquera, Bhargavi Paranjabe, Adina Williams, Tal Linzen, Ryan Cotterell
Venue:
CoNLL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
253–258
Language:
URL:
https://aclanthology.org/2023.conll-babylm.21
DOI:
10.18653/v1/2023.conll-babylm.21
Bibkey:
Cite (ACL):
Lukas Wolf, Klemen Kotar, Greta Tuckute, Eghbal Hosseini, Tamar I. Regev, Ethan Gotlieb Wilcox, and Alexander Scott Warstadt. 2023. WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words. In Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning, pages 253–258, Singapore. Association for Computational Linguistics.
Cite (Informal):
WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words (Wolf et al., CoNLL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.conll-babylm.21.pdf