CRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech Translation
cs.CL, cs.SD
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/pe-trik/OmniSTEval
Terminology
Sources
- Efficient Monotonic Multihead Attention
- Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection
- Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent
- Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice
- Simultaneous Speech-to-Speech Translation Without Aligned Data
- Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech
- Qwen2.5-Omni Technical Report
- StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model
- SHAS: Approaching optimal Segmentation for End-to-End Speech Translation
- Sequence Transduction with Recurrent Neural Networks
- Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translation
- Qwen3 Technical Report
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data