论文标题
学习通过平滑的最大池来检测关键字零件和整个零件
Learning To Detect Keyword Parts And Whole By Smoothed Max Pooling
论文作者
论文摘要
我们提出了平滑的最大池损失及其在关键字点斑点系统中的应用。所提出的方法共同训练编码器（检测关键字零件）和以半监督的方式进行解码器（以检测整个关键字）。提出的新损失功能允许训练模型检测部分和整个关键字，而无需严格取决于LVCSR的框架级标签（大词汇连续语音识别），从而使进一步的优化成为可能。由于优化性的提高，所提出的系统在[1]中优于基线关键字斑点模型。此外，由于对LVCSR的依赖性降低，因此可以更容易地适用于设备学习应用程序。
We propose smoothed max pooling loss and its application to keyword spotting systems. The proposed approach jointly trains an encoder (to detect keyword parts) and a decoder (to detect whole keyword) in a semi-supervised manner. The proposed new loss function allows training a model to detect parts and whole of a keyword, without strictly depending on frame-level labeling from LVCSR (Large vocabulary continuous speech recognition), making further optimization possible. The proposed system outperforms the baseline keyword spotting model in [1] due to increased optimizability. Further, it can be more easily adapted for on-device learning applications due to reduced dependency on LVCSR.
