arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.03052cs.CLcs.SDeess.AS
收藏

视觉作为中介语:学习非转录语音的多语言语义嵌入

Vision as an Interlingua: Learning Multilingual Semantic Embeddings of Untranscribed Speech

Massachusetts Institute of Technology(麻省理工学院)

David Harwath, Galen Chuang, James Glass

摘要:

在本文中,我们探讨了学习的神经网络嵌入自然图像和语音波形描述这些图像的内容。这些嵌入是直接从波形中学习的,而不使用语言transmitting或传统的语音识别技术。虽然以前的工作已经调查了这种设置在单语的情况下使用英语语音数据,这项工作是第一次努力将这些技术应用到英语以外的语言。使用英语和印地语收集的口头字幕,我们表明,相同的模型架构可以成功地应用于这两种语言。此外,我们还证明了在两种语言上同时训练多语言模型可以提高单语模型的性能。最后,我们表明,这些模型能够执行语义跨语言语音到语音检索。

英文摘要:

In this paper, we explore the learning of neural network embeddings for natural images and speech waveforms describing the content of those images. These embeddings are learned directly from the waveforms without the use of linguistic transcriptions or conventional speech recognition technology. While prior work has investigated this setting in the monolingual case using English speech data, this work represents the first effort to apply these techniques to languages beyond English. Using spoken captions collected in English and Hindi, we show that the same model architecture can be successfully applied to both languages. Further, we demonstrate that training a multilingual model simultaneously on both languages offers improved performance over the monolingual models. Finally, we show that these models are capable of performing semantic cross-lingual speech-to-speech retrieval.

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。

↑