English(EN) Simultaneous Speech-to-Speech Translation Without Aligned Data

Hibiki-Zero语音翻译模型消除了对齐数据的需求

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-23 04:00

研究人员开发了Hibiki-Zero，一种新颖的语音到语音翻译系统，无需词级对齐数据。这种方法简化了训练，并允许更容易地适应各种语言。该系统首先在句子级对齐数据上进行训练，以实现高延迟翻译，然后使用带有GRPO的强化学习策略来优化低延迟，同时保持翻译质量。Hibiki-Zero在五个语言对上展示了最先进的性能，并且可以用最少的数据适应新语言。 AI

影响该模型可以显著降低开发语音翻译系统的数据要求，从而实现更广泛的语言支持和更快的部署。

排序理由详细介绍新模型和语音翻译方法的论文。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍新模型和语音翻译方法的论文。[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, model release; 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: 76 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Tom Labiausse, Romain Fabre, Yannick Est\`eve, Alexandre D\'efossez, Neil Zeghidour · 2026-07-23 04:00

无需对齐数据即可进行同步语音到语音翻译

arXiv:2602.11072v2 Announce Type: replace Abstract: Simultaneous speech translation requires translating source speech into a target language in real-time while handling non-monotonic word dependencies. Traditional approaches rely on supervised training with word-level aligned da…

本文如何被排名

报道来源 [1]

无需对齐数据即可进行同步语音到语音翻译

相关实体

相关话题