EMMeTT: Efficient Multimodal Machine Translation Training

EMMeTT: Efficient Multimodal Machine Translation Training

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024

20 September 2024

Piotr Żelasko

Zhehuai Chen

Oleksii Hrinchuk

Jagadeesh Balam

Vitaly Lavrukhin

Boris Ginsburg

ArXiv (abs)PDF HTML

Papers citing "EMMeTT: Efficient Multimodal Machine Translation Training"

3 / 3 papers shown

Title
Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Training Framework Wenhao Tang Heng Fang Ge Wu Xiang Li Ming-Ming Cheng 183 0 0 25 Sep 2025
Training and Inference Efficiency of Encoder-Decoder Speech Models Piotr .Zelasko Kunal Dhawan Daniel Galvez Krishna Puvvada Ankita Pasad Nithin Rao Koluguri Ke Hu Vitaly Lavrukhin Jagadeesh Balam Boris Ginsburg 305 8 0 07 Mar 2025
VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-TuningNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 Yifan Peng Krishna Puvvada Zhehuai Chen Piotr .Zelasko He Huang Kunal Dhawan Ke Hu Shinji Watanabe Jagadeesh Balam Boris Ginsburg 313 7 0 23 Oct 2024