Simultaneous Speech Translation (SimulST) requires balancing high translation quality with low latency. Recent work introduced REINA, a method that trains a Read/Write policy based on estimating the information gain of reading more audio. However, we find that information-based policies often lack temporal context, leading the policy to bias itself toward reading most of the audio before starting to write. We improve REINA using two distinct strategies: a supervised alignment network (REINA-SAN) and a timestep-augmented network (REINA-TAN). Our results demonstrate that while both methods significantly outperform the baseline and resolve stability issues, REINA-TAN provides a slightly superior Pareto frontier for streaming efficiency, whereas REINA-SAN offers more robustness against 'read loops'. Applied to Whisper, both methods improve the pareto frontier of streaming efficiency as measured by Normalized Streaming Efficiency (NoSE) scores up to 7.1% over existing competitive baselines.
@article{arxiv.2604.09916,
title = {Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation},
author = {Joseph Liu and Nameer Hirschkind and Xiao Yu and Mahesh Kumar Nandwana},
journal= {arXiv preprint arXiv:2604.09916},
year = {2026}
}