顺序路由框架：完全基于胶囊网络的语音识别
Sequential Routing Framework: Fully Capsule Network-based Speech Recognition
摘要：
胶囊网络（CapsNets）最近作为一种新的神经结构受到关注。本文介绍了顺序路由框架，我们认为这是第一种方法，以适应CapsNet的结构，序列到序列的识别。输入序列被封装，然后按窗口大小切片。通过迭代路由机制，每个切片在相应的时间被分类为标签。之后，损失通过连接主义时间分类（CTC）计算。在路由过程中，所需的参数数量可以通过在切片上共享可学习的权重来控制，而不管序列的长度如何。我们还提出了一个顺序的动态路由算法，以取代传统的动态路由。所提出的技术可以最小化由路由迭代引起的解码速度下降，因为它可以以非迭代方式操作而不降低精度。与基于双向长短期记忆的CTC网络相比，该方法在《华尔街日报》语料库上的单词错误率为16.9%，降低了1.1%。在TIMIT语料库上，与基于卷积神经网络的CTC网络相比，它的电话错误率降低了0.7%，为17.5%（Zhang et al.，2016）。
英文摘要：
Capsule networks (CapsNets) have recently gotten attention as a novel neural architecture. This paper presents the sequential routing framework which we believe is the first method to adapt a CapsNet-only structure to sequence-to-sequence recognition. Input sequences are capsulized then sliced by a window size. Each slice is classified to a label at the corresponding time through iterative routing mechanisms. Afterwards, losses are computed by connectionist temporal classification (CTC). During routing, the required number of parameters can be controlled by the window size regardless of the length of sequences by sharing learnable weights across the slices. We additionally propose a sequential dynamic routing algorithm to replace traditional dynamic routing. The proposed technique can minimize decoding speed degradation caused by the routing iterations since it can operate in a non-iterative manner without dropping accuracy. The method achieves a 1.1% lower word error rate at 16.9% on the Wall Street Journal corpus compared to bidirectional long short-term memory-based CTC networks. On the TIMIT corpus, it attains a 0.7% lower phone error rate at 17.5% compared to convolutional neural network-based CTC networks (Zhang et al., 2016).
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。
