论文标题
用于流whord检测的小足迹卷积卷积反复网络
Small Footprint Convolutional Recurrent Networks for Streaming Wakeword Detection
论文作者
论文摘要
在这项工作中，我们提出了适用于WakeWord检测问题的小范围卷积复发网络模型，并以缩放点产品的关注增强了它们。我们发现，与250K参数预算中的卷积神经网络模型相比，可以通过使用CRNN减少参数大小的10％，而我们可以以50K参数预算提高32％，而参数尺寸降低了75％，而参数尺寸比单词级别的密度密度浓度的神经网络模型降低了75％。我们讨论了与CRNN一起对流音频进行推断的具有挑战性问题的解决方案，以及与CNN，DNN和DNN-HMM模型相比，起始端子索引错误和延迟的差异。
In this work, we propose small footprint Convolutional Recurrent Neural Network models applied to the problem of wakeword detection and augment them with scaled dot product attention. We find that false accepts compared to Convolutional Neural Network models in a 250k parameter budget can be reduced by 25% with a 10% reduction in parameter size by using CRNNs, and we can get up to 32% improvement at a 50k parameter budget with 75% reduction in parameter size compared to word-level Dense Neural Network models. We discuss solutions to the challenging problem of performing inference on streaming audio with CRNNs, as well as differences in start-end index errors and latency in comparison to CNN, DNN, and DNN-HMM models.
