arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.03382cs.CLcs.SDeess.AS
收藏

高保真同时语音到语音翻译

High-Fidelity Simultaneous Speech-To-Speech Translation

Kyutai

Tom Labiausse, Laurent Mazaré, Edouard Grave, Patrick Pérez, Alexandre Défossez, Neil Zeghidour

AI总结:

本文提出Hibiki,一种基于多流语言模型的仅解码器同时语音翻译模型,通过弱监督方法学习逐词延迟,实现高质量、高保真的实时语音到语音翻译,并在法英任务上达到最先进性能。

摘要:

我们介绍了Hibiki,一种用于同时语音翻译的仅解码器模型。Hibiki利用多流语言模型同步处理源语音和目标语音,并联合生成文本和音频标记以执行语音到文本和语音到语音翻译。此外,我们解决了同声传译的基本挑战,与逐句翻译(等待源话语结束后才开始翻译)不同,同声传译调整其流程,以累积足够的上下文,逐块实时生成正确的翻译。为此,我们引入了一种弱监督方法,利用现成文本翻译系统的困惑度来识别每个单词的最佳延迟,并创建对齐的合成数据。经过监督训练后,Hibiki通过普通的温度采样执行自适应、同时的语音翻译。在法英同时语音翻译任务中,Hibiki在翻译质量、说话人保真度和自然度方面展示了最先进的性能。此外,其推理过程的简单性使其兼容批量翻译,甚至可在设备上实时部署。我们提供了示例以及模型和推理代码。

英文摘要:

We introduce Hibiki, a decoder-only model for simultaneous speech translation. Hibiki leverages a multistream language model to synchronously process source and target speech, and jointly produces text and audio tokens to perform speech-to-text and speech-to-speech translation. We furthermore address the fundamental challenge of simultaneous interpretation, which unlike its consecutive counterpart, where one waits for the end of the source utterance to start translating, adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk. To do so, we introduce a weakly-supervised method that leverages the perplexity of an off-the-shelf text translation system to identify optimal delays on a per-word basis and create aligned synthetic data. After supervised training, Hibiki performs adaptive, simultaneous speech translation with vanilla temperature sampling. On a French-English simultaneous speech translation task, Hibiki demonstrates state-of-the-art performance in translation quality, speaker fidelity and naturalness. Moreover, the simplicity of its inference process makes it compatible with batched translation and even real-time on-device deployment. We provide examples as well as models and inference code.

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。

↑