LLM Digest

Story

arxiv_cs_cl · Nov 9, 2026 · paper

Source brief

Text Grouping Changes Completion-Time Comparisons in Long-Form Simultaneous Speech Translation

arxiv.orgNov 9, 2026
original source linked

In brief

Does grouping translation updates before speech synthesis change the measured completion gap between two translators? We compare StreamAtt with its fixed-audio-history baseline on ten English-German talks. For each translation, we keep the intended text and its availability times

Read the original at arxiv.org →Open in live feed Read that day’s brief

Text Grouping Changes Completion-Time Comparisons in Long-Form Simultaneous Speech Translation

Earlier in this thread 4 items

CRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech Translation

Speech translation in Google Meet is now rolling out to mobile devices

Path-Level Structural and Semantic Alignment for Hierarchical Multi-Label Text Classification

BridgeKV: Large-Model Prefill and Small-Model Decoding for LLM Inference via KV Cache Translation