arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.01578cs.CL
收藏

基于CTC的语音直接翻译压缩

CTC-based Compression for Direct Speech Translation

Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会);University of Trento(特伦托大学)

Marco Gaido, Mauro Cettolo, Matteo Negri, Marco Turchi

摘要:

先前的研究表明,输入音频的动态音素通知压缩有利于语音翻译(ST)。然而,他们需要一个专用的电话识别模型,并且没有测试这种直接ST的解决方案,其中单个模型将输入音频翻译成目标语言,而没有中间表示。在这项工作中,我们提出了第一种方法,能够执行的输入间接ST模型的动态压缩。特别是,我们利用连接时间分类(CTC)压缩输入序列根据其语音特征。我们的实验表明,我们的解决方案在两种语言对(英语-意大利语和英语-德语)的强基线上带来了1.3-1.5的BLEU改进,上下文减少了10%以上的内存占用。

英文摘要:

Previous studies demonstrated that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST). However, they required a dedicated model for phone recognition and did not test this solution for direct ST, in which a single model translates the input audio into the target language without intermediate representations. In this work, we propose the first method able to perform a dynamic compression of the input indirect ST models. In particular, we exploit the Connectionist Temporal Classification (CTC) to compress the input sequence according to its phonetic characteristics. Our experiments demonstrate that our solution brings a 1.3-1.5 BLEU improvement over a strong baseline on two language pairs (English-Italian and English-German), contextually reducing the memory footprint by more than 10%.

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。

↑