论文标题
域意识培训远场小英寸关键字斑点
Domain Aware Training for Far-field Small-footprint Keyword Spotting
论文作者
论文摘要
在本文中，我们将重点放在远场场景下的小英尺打印关键字斑点的任务上。远场环境通常在现实生活中的语音应用中遇到，导致由于房间混响和各种噪音而导致的性能严重下降。我们的基线系统建立在卷积神经网络上，该网络训练有远场和封闭式语音的汇总数据。为了应对扭曲，我们开发了三个领域意识训练系统，包括域嵌入系统，深珊瑚系统和多任务学习系统。这些方法将域知识纳入网络培训中，并提高关键字分类器在远场条件下的性能。实验结果表明，我们提出的方法设法在封闭式语音上保持了绩效，并在远场测试集上取得了重大改进。
In this paper, we focus on the task of small-footprint keyword spotting under the far-field scenario. Far-field environments are commonly encountered in real-life speech applications, causing severe degradation of performance due to room reverberation and various kinds of noises. Our baseline system is built on the convolutional neural network trained with pooled data of both far-field and close-talking speech. To cope with the distortions, we develop three domain aware training systems, including the domain embedding system, the deep CORAL system, and the multi-task learning system. These methods incorporate domain knowledge into network training and improve the performance of the keyword classifier on far-field conditions. Experimental results show that our proposed methods manage to maintain the performance on the close-talking speech and achieve significant improvement on the far-field test set.
