arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.09693cs.CL
收藏

从字幕到分割:改进低资源语音到文本翻译流水线

Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines

Columbia University(哥伦比亚大学);University of Edinburgh(爱丁堡大学)

David Wan, Zhengping Jiang, Chris Kedzie, Elsbeth Turcan, Peter Bell, Kathleen McKeown

摘要:

在这项工作中,我们专注于改善ASR输出分割的背景下,低资源的语言语音到文本的翻译。ASR输出分段是至关重要的,因为ASR系统使用纯声学信息对输入音频进行分段,并且不能保证输出类似音乐的分段。由于大多数机器翻译系统都希望将句子作为输入,因此输入较长的未分段段落可能会导致次优性能。我们探讨了使用电视节目和电影的字幕数据集来训练更好的ASR分割模型的可行性。我们进一步将词性(POS)标签和依赖标签信息(来自未分割的ASR输出)纳入我们的分割模型。我们表明,这种嘈杂的句法信息可以提高模型的准确性。我们评估我们的模型内在的分割质量和extramination上下游MT性能,以及下游任务,包括跨语言信息检索(CLIR)任务和人类相关性评估。我们的模型显示立陶宛语和保加利亚语的下游任务性能有所提高。

英文摘要:

In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation. ASR output segmentation is crucial, as ASR systems segment the input audio using purely acoustic information and are not guaranteed to output sentence-like segments. Since most MT systems expect sentences as input, feeding in longer unsegmented passages can lead to sub-optimal performance. We explore the feasibility of using datasets of subtitles from TV shows and movies to train better ASR segmentation models. We further incorporate part-of-speech (POS) tag and dependency label information (derived from the unsegmented ASR outputs) into our segmentation model. We show that this noisy syntactic information can improve model accuracy. We evaluate our models intrinsically on segmentation quality and extrinsically on downstream MT performance, as well as downstream tasks including cross-lingual information retrieval (CLIR) tasks and human relevance assessments. Our model shows improved performance on downstream tasks for Lithuanian and Bulgarian.

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。

↑