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 2102.01013cs.CLcs.SDeess.AS
收藏

End2End声学到语义转换

End2End Acoustic to Semantic Transduction

LIUM - Le Mans University(勒芒大学计算机科学实验室);LIA - Avignon University(阿维尼翁大学计算机科学实验室);McGill University(麦吉尔大学)

Valentin Pelloin, Nathalie Camelin, Antoine Laurent, Renato De Mori, Antoine Caubrière, Yannick Estève, Sylvain Meignier

摘要:

在本文中,我们提出了一个新的端到端序列到序列的口语语言理解模型使用注意力机制。它可靠地选择上下文声学特征,以假设语义内容。设计并测试了一个能够从声学跨度中提取所有发音单词和概念的初始架构。该系统采用浅层融合语言模型,在法语媒体语料库上实现了13.6的概念出错率和18.5的概念值出错率,与现有技术相比降低了2.8个百分点。该转导达到15.4 CER和21.6 CVER,而没有任何新类型的上下文。

英文摘要:

In this paper, we propose a novel end-to-end sequence-to-sequence spoken language understanding model using an attention mechanism. It reliably selects contextual acoustic features in order to hypothesize semantic contents. An initial architecture capable of extracting all pronounced words and concepts from acoustic spans is designed and tested. With a shallow fusion language model, this system reaches a 13.6 concept error rate (CER) and an 18.5 concept value error rate (CVER) on the French MEDIA corpus, achieving an absolute 2.8 points reduction compared to the state-of-the-art. Then, an original model is proposed for hypothesizing concepts and their values. This transduction reaches a 15.4 CER and a 21.6 CVER without any new type of context.

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。

↑