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 1907.04536cs.LGcs.SDeess.ASstat.ML
收藏

语音关键词识别的多层注意力机制

Multi-layer Attention Mechanism for Speech Keyword Recognition

Sichuan University(四川大学)

Ruisen Luo, Tianran Sun, Chen Wang, Miao Du, Zuodong Tang, Kai Zhou, Xiaofeng Gong, Xiaomei Yang

摘要:

语音关键词自动识别作为语音识别技术的重要组成部分,近年来得到了广泛的研究。这种技术在基础设施和计算资源有限的情况下变得特别关键,例如车辆中的语音命令识别和机器人交互。目前,语音关键词自动识别的主流方法是基于带有注意力机制的长短期记忆(LSTM)网络。然而,由于在特征提取期间导致的LSTM层的不可避免的信息损失,计算的注意力权重是有偏差的。本文提出了一种新的方法,即多层注意力机制,以处理不准确的注意力权重的问题。其核心思想是,除了传统的注意力机制,在特征提取和LSTM之前的层的信息被引入到注意力权重计算中。因此,注意力权重更准确,因为整个模型可以具有更精确和集中的区域。我们在Google Speech Command数据集V2数据集上对卷积神经网络,双向LSTM循环神经网络和循环神经网络的关键词定位性能进行了全面的比较和分析,并提出了注意力机制。实验结果表明,该方法具有良好的效果,证明了该方法的有效性。所提出的多层注意方法可以为其他与目标识别相关的研究提供参考。

英文摘要:

As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and computational resources, such as voice command recognition in vehicles and robot interaction. At present, the mainstream methods in automatic speech keyword recognition are based on long short-term memory (LSTM) networks with attention mechanism. However, due to inevitable information losses for the LSTM layer caused during feature extraction, the calculated attention weights are biased. In this paper, a novel approach, namely Multi-layer Attention Mechanism, is proposed to handle the inaccurate attention weights problem. The key idea is that, in addition to the conventional attention mechanism, information of layers prior to feature extraction and LSTM are introduced into attention weights calculations. Therefore, the attention weights are more accurate because the overall model can have more precise and focused areas. We conduct a comprehensive comparison and analysis on the keyword spotting performances on convolution neural network, bi-directional LSTM cyclic neural network, and cyclic neural network with the proposed attention mechanism on Google Speech Command datasets V2 datasets. Experimental results indicate favorable results for the proposed method and demonstrate the validity of the proposed method. The proposed multi-layer attention methods can be useful for other researches related to object spotting.

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。

↑