Papers
arxiv:2611.12501

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

Published on Nov 9
Authors:
,

Abstract

Grouping translation updates before speech synthesis can either increase or decrease the measured completion lead depending on the synthesizer, and it can leave paired audio unchanged while delaying completion in continuing CosyVoice 3 sessions, so speech-timing comparisons must specify how text enters synthesis.

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 fixed and vary how updates are grouped for synthesis. Four-second grouping increases StreamAtt's mean completion lead from 106.6 to 229.1 seconds with XTTS-v2, but reduces it from 169.5 to 146.5 seconds with Piper. Both produce shorter audio; different changes in playback idle account for the opposite effects. These directions recur on a separately selected twenty-talk panel. In continuing CosyVoice 3 sessions, grouping instead leaves paired audio unchanged and delays completion on nineteen of twenty blocks. A speech-timing comparison therefore needs to specify how text enters synthesis, not just which synthesizer is used. Recognition and automatic word timing describe the outputs, but do not establish translation accuracy or intelligibility.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2611.12501
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.12501 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/2611.12501 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/2611.12501 in a Space README.md to link it from this page.

Collections including this paper 1