English(EN) Learning Timeline-Preserving Speech-to-Speech Translation

新的TransDubber系统在翻译中保留语音时序

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-04 05:00

研究人员开发了TransDubber，一种新颖的端到端自回归语音到语音翻译系统，专注于保留原始语音的时间结构。这种新方法旨在不仅匹配内容和声音，还匹配语音和停顿的确切时序，这对于配音等应用至关重要。TransDubber通过直接从对齐的目标波形学习并采用结合了渐进式监督学习和强化学习的训练策略来实现这一点，与现有方法相比，在保持翻译质量的同时，显著提高了时长匹配和停顿对齐效果。 AI

影响这项研究通过关注时间对齐，推进了语音到语音翻译技术，有望改善配音和其他对时间敏感的应用。

排序理由详细介绍新模型和方法的学术论文。[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 →

本文如何被排名

Signal score: 41 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍新模型和方法的学术论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Zhisheng Zheng, David Harwath · 2026-11-04 05:00

学习时间轴保留的语音到语音翻译

arXiv:2611.00690v1 Announce Type: cross Abstract: Speech-to-speech translation (S2ST) increasingly preserves what is said and how it sounds, but not necessarily when speech and silence occur. For dubbing and other temporally grounded applications, matching total duration is not e…

本文如何被排名

报道来源 [1]

学习时间轴保留的语音到语音翻译

相关实体

相关话题