arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1803.05563cs.CL
收藏

基于注意力模型的联结主义时间分类

Advancing Connectionist Temporal Classification With Attention Modeling

Microsoft(微软)

Amit Das, Jinyu Li, Rui Zhao, Yifan Gong

摘要:

在这项研究中,我们提出了推进全神经语音识别直接将注意力建模的连接时间分类(CTC)框架。特别是,我们使用时间卷积特征来推导新的上下文向量,以将注意力建模为CTC网络的一部分。为了进一步改进注意力建模,我们利用从表示隐式语言模型的网络中提取的内容信息。最后,我们引入了基于向量的注意力权重,这些权重应用于时间和各个分量的上下文向量。我们评估我们的系统上3400小时的Microsoft Cortana语音助手任务,并证明我们提出的模型始终优于基线模型,实现约20%的相对减少字出错率。

英文摘要:

In this study, we propose advancing all-neural speech recognition by directly incorporating attention modeling within the Connectionist Temporal Classification (CTC) framework. In particular, we derive new context vectors using time convolution features to model attention as part of the CTC network. To further improve attention modeling, we utilize content information extracted from a network representing an implicit language model. Finally, we introduce vector based attention weights that are applied on context vectors across both time and their individual components. We evaluate our system on a 3400 hours Microsoft Cortana voice assistant task and demonstrate that our proposed model consistently outperforms the baseline model achieving about 20% relative reduction in word error rates.

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。

↑