PulseAugur
中
实时 06:30:51
English(EN) Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning

Kraken LLM 提升语音到语音翻译质量

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员开发了Kraken，一种利用LLM和低比特率向量量化来提高质量和保留非语言信息的新型语音到语音翻译模型。该模型基于Qwen3-8B构建，使用一个独立的解码器Autowave-X，该解码器以源语音为条件，以增强说话者和韵律的传递。在对150,000小时多语言数据进行的评估中，Kraken在翻译质量上优于SeamlessM4T-Large v2和Qwen2.5 Omni。 AI

影响 这项研究可能带来更自然、更准确的语音到语音翻译系统，从而改善跨语言交流。

排序理由 该集群包含一篇详细介绍新模型及其技术方法的 ist 研究论文。[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 →

Kraken LLM 提升语音到语音翻译质量

本文如何被排名

Signal score
30 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍新模型及其技术方法的 ist 研究论文。[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
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]

  1. arXiv cs.CL TIER_1 English(EN) · Hayato Futami, Hassan Shahmohammadi, Tushar Dhyani, Alkis Koudounas, Rapha\"el Lafargue, Yosuke Kashiwagi, Quentin Jodelet, Emiru Tsunoo ·

    Kraken：基于LLM的低比特率VQ和双路径源条件语音到语音翻译

    arXiv:2609.13045v1 Announce Type: new Abstract: Speech-to-speech translation (S2ST) has advanced significantly with speech LLMs, offering the potential for joint optimization and preserving non-linguistic information. However, these models struggle with predicting high-bitrate sp…

相关实体

相关话题