Papers
arxiv:2312.04515
Efficient Monotonic Multihead Attention
Published on Dec 7, 2023
·
Featured in Daily Papers
on Dec 8, 2023
Authors:
Abstract
We introduce the Efficient Monotonic Multihead Attention (EMMA), a state-of-the-art simultaneous translation model with numerically-stable and unbiased monotonic alignment estimation. In addition, we present improved training and inference strategies, including simultaneous fine-tuning from an offline translation model and reduction of monotonic alignment variance. The experimental results demonstrate that the proposed model attains state-of-the-art performance in simultaneous speech-to-text translation on the Spanish and English translation task.
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2312.04515 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2312.04515 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2312.04515 in a Space README.md to link it from this page.