arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2004.11419cs.SDcs.CLeess.AS
收藏

端到端语音到对话行为识别

End-to-end speech-to-dialog-act recognition

Kyoto University(京都大学)

Viet-Trung Dang, Tianyu Zhao, Sei Ueno, Hirofumi Inaguma, Tatsuya Kawahara

摘要:

提取话语中的意图和/或语义概念的口语语言理解通常被公式化为自动语音识别的后处理。它通常使用Oracle脚本进行训练,但需要通过ASR处理错误。此外,还有一些与意图相关但没有用转录本表示的声学特征。在本文中,我们提出了一个端到端的模型,直接将语音转换成对话行为,而不确定性的转录过程。在该模型中,对话行为识别网络在softmax层之前的潜在层与声学到单词ASR模型相结合,该模型提供了单词级ASR解码信息的分布式表示。然后,整个网络以端到端的方式进行微调。这允许稳定的训练以及对ASR错误的鲁棒性。该模型进一步扩展,进行DA分割联合。与Switchboard语料库的评估表明,该方法显着提高了对话行为识别的准确性从传统的管道框架。

英文摘要:

Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to deal with errors by ASR. Moreover, there are acoustic features which are related with intents but not represented with the transcripts. In this paper, we present an end-to-end model which directly converts speech into dialog acts without the deterministic transcription process. In the proposed model, the dialog act recognition network is conjunct with an acoustic-to-word ASR model at its latent layer before the softmax layer, which provides a distributed representation of word-level ASR decoding information. Then, the entire network is fine-tuned in an end-to-end manner. This allows for stable training as well as robustness against ASR errors. The model is further extended to conduct DA segmentation jointly. Evaluations with the Switchboard corpus demonstrate that the proposed method significantly improves dialog act recognition accuracy from the conventional pipeline framework.

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。

↑