arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.02629cs.CL
收藏

高效且具竞争力的语音翻译:FBK@IWSLT2022

Efficient yet Competitive Speech Translation: FBK@IWSLT2022

Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会);University of Trento(特伦托大学);NVIDIA AI Technology Center(英伟达人工智能技术中心)

Marco Gaido, Sara Papi, Dennis Fucci, Giuseppe Fiameni, Matteo Negri, Marco Turchi

AI总结:

FBK在IWSLT 2022中提出轻量级语音翻译策略,通过去除ASR预训练、数据过滤和解决音频分割不匹配来降低训练成本,并在保持翻译质量的同时取得显著提升。

摘要:

FBK提交至IWSLT 2022离线和同声语音翻译任务的系统的主要目标是,在不牺牲翻译质量的前提下降低模型训练成本。为此,我们首先质疑了ASR预训练的必要性,表明它并非取得有竞争力结果的必要条件。其次,我们关注数据过滤,表明一种查看源端和目标端字符之间比率的简单方法带来了1 BLEU的质量提升。第三,我们比较了不同方法,以减少训练数据(在句子级别手动分割)和推理数据(自动分割)之间的音频分割不匹配的有害影响。为了实现同样的降低训练成本目标,我们使用为离线ST训练的相同模型参与同声任务。我们在MuST-C en-de语料库上获得的高分(26.7 BLEU)证明了我们轻量级训练策略的有效性,并在高资源数据条件下得到了证实:在IWSLT2020测试集上较去年的获胜系统提升了1.6 BLEU。

英文摘要:

The primary goal of this FBK's systems submission to the IWSLT 2022 offline and simultaneous speech translation tasks is to reduce model training costs without sacrificing translation quality. As such, we first question the need of ASR pre-training, showing that it is not essential to achieve competitive results. Second, we focus on data filtering, showing that a simple method that looks at the ratio between source and target characters yields a quality improvement of 1 BLEU. Third, we compare different methods to reduce the detrimental effect of the audio segmentation mismatch between training data manually segmented at sentence level and inference data that is automatically segmented. Towards the same goal of training cost reduction, we participate in the simultaneous task with the same model trained for offline ST. The effectiveness of our lightweight training strategy is shown by the high score obtained on the MuST-C en-de corpus (26.7 BLEU) and is confirmed in high-resource data conditions by a 1.6 BLEU improvement on the IWSLT2020 test set over last year's winning system.

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。

↑