PulseAugur
中
实时 10:26:11
English(EN) Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech Translation

新方法改善了同步语音翻译的质量-延迟权衡

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员开发了一种新的端到端同步语音翻译方法，通过使用前缀监督来调整全句语音语言模型，从而改善了质量-延迟权衡。该方法在三个语言方向的 FLEURS 和 CoVoST2 数据集上进行了测试，使用置信度阈值来管理推理时间性能，并探索了单轮和多轮解码策略。特别是多轮解码显著减少了提交校准错误，尤其是在早期前缀时，从而实现了更一致、更准确的翻译。 AI

影响 通过提高语音到文本系统的准确性和降低延迟来增强实时翻译能力。

排序理由 详细介绍语音翻译新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新方法改善了同步语音翻译的质量-延迟权衡

本文如何被排名

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍语音翻译新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Hieu Hoang, Amittai Axelrod ·

    从部分语音中学习何时提交以实现端到端同步语音翻译

    arXiv:2610.02612v1 Announce Type: new Abstract: Simultaneous speech translation must emit useful target text before the source is complete while preserving every committed token. We adapt a full-utterance speech language model using prefix supervision derived from its own complet…

相关实体

相关话题