Seed LiveInterpret 2.0：用你自己的声音实现端到端同声语音转语音翻译
Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice
AI总结：
针对现有产品级同声传译系统质量差、延迟高、多说话人混淆等问题，研究提出端到端模型Seed-LiveInterpret 2.0，依托双工理解-生成框架，结合预训练与强化学习，在翻译质量上优于商用方案，延迟降至3秒，大幅提升实用性。
摘要：
同声传译（SI）是翻译行业最具挑战性的前沿领域之一，产品级自动系统长期受诸多棘手问题困扰：转录和翻译质量欠佳、缺乏实时语音生成、多说话人混淆，以及翻译语音冗余膨胀，在长篇语篇中尤为突出。本研究推出Seed-LiveInterpret 2.0，这是一款端到端同声传译模型，可生成高保真、超低延迟的语音转语音内容，还具备声音克隆功能。作为一套可完全落地的产品级解决方案，Seed-LiveInterpret 2.0依托我们提出的新型双工语音转语音理解-生成框架，直面并攻克上述难题。实验结果表明，通过大规模预训练和强化学习，该模型在翻译准确率与延迟之间实现了显著更优的平衡，经人工译员验证，在复杂场景下的正确率超过70%。值得注意的是，Seed-LiveInterpret 2.0的翻译质量大幅优于商用同声传译解决方案，同时将克隆语音的平均延迟从近10秒降至接近实时的3秒，降幅接近70%，极大提升了实际可用性。
英文摘要：
Simultaneous Interpretation (SI) represents one of the most daunting frontiers in the translation industry, with product-level automatic systems long plagued by intractable challenges: subpar transcription and translation quality, lack of real-time speech generation, multi-speaker confusion, and translated speech inflation, especially in long-form discourses. In this study, we introduce Seed-LiveInterpret 2.0, an end-to-end SI model that delivers high-fidelity, ultra-low-latency speech-to-speech generation with voice cloning capabilities. As a fully operational product-level solution, Seed-LiveInterpret 2.0 tackles these challenges head-on through our novel duplex speech-to-speech understanding-generating framework. Experimental results demonstrate that through large-scale pretraining and reinforcement learning, the model achieves a significantly better balance between translation accuracy and latency, validated by human interpreters to exceed 70% correctness in complex scenarios. Notably, Seed-LiveInterpret 2.0 outperforms commercial SI solutions by significant margins in translation quality, while slashing the average latency of cloned speech from nearly 10 seconds to a near-real-time 3 seconds, which is around a near 70% reduction that drastically enhances practical usability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
