Attention-Based Adaptive Policies for Simultaneous Speech-to-Text Translation

arXiv:2609.30839 · cs.LG · Submitted 2026-09-25 · Read on arXiv

cs.LG

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Recent Frame Attention Policy — 5× in this paper
• Dual-Condition Attention Policy — 4× in this paper
• Local Agreement — 4× in this paper
• Alignment — 3× in this paper · explained in 1 episode
• Attention Mechanism — 3× in this paper · explained in 3 episodes
• Cross-Attention Mechanism — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Average Lagging — 1× in this paper

Sources

• SimulEval: An Evaluation Toolkit for Simultaneous Translation
• Recent Advances in End-to-End Simultaneous Speech Translation
• SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation
• Gaussian Multi-head Attention for Simultaneous Machine Translation
• Efficient Monotonic Multihead Attention
• AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation
• CVSS Corpus and Massively Multilingual Speech-to-Speech Translation
• StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
• Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks