PulseAugur
中
实时 22:14:06
English(EN) Real-time speech-to-speech translation

Google DeepMind 发布实时语音保留式语音翻译

Google DeepMind 开发了一个端到端的语音到语音翻译(S2ST)模型,该模型能够实时翻译口语,同时保留原始说话者的声音和情感,延迟仅为两秒。这种新架构摒弃了传统的级联系统(这些系统存在显著延迟和错误累积问题),采用了流式框架和可扩展的数据采集流水线。另外,研究人员还推出了 STEB,这是一个新的基准测试,旨在评估 S2ST 系统不仅在翻译准确性方面,还在保留情感、场景风格和非语言发声等表达属性方面的能力,并指出当前系统在这些细微之处仍有不足。 AI

影响 这种在实时、语音保留式 S2ST 方面的进步可以显著增强跨语言交流,使互动更加自然和个性化。

排序理由 Google DeepMind,一个前沿实验室,宣布了一个具有新颖架构和性能指标的新 S2ST 模型。 [lever_c_demoted from frontier_release: ic=2 ai=1.0]

在 Google AI / Research 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Google DeepMind 发布实时语音保留式语音翻译

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
Significant
Google DeepMind,一个前沿实验室,宣布了一个具有新颖架构和性能指标的新 S2ST 模型。 [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product
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
362 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 [2]

  1. Google AI / Research TIER_1 English(EN) ·

    实时语音到语音翻译

    Algorithms & Theory

  2. arXiv cs.AI TIER_1 English(EN) · Wei Xue ·

    STEB:一个用于评估超越翻译保真度的语音到语音翻译表现基准

    Speech-to-speech translation (S2ST) should preserve not only lexical meaning, but also expressive attributes: emotion, scenario style (e.g., news reporting vs. dramatic dialogue), and nonverbal vocalizations (NVs). Moreover, collecting cross-lingual target speech that is both tra…