Sequential Routing Framework: Fully Capsule Network-based Speech Recognition

07/23/2020
by   Kyungmin Lee, et al.
0

Capsule networks (CapsNets) have recently gotten attention as alternatives for convolutional neural networks (CNNs) with their greater hierarchical representation capabilities. In this paper, we introduce the sequential routing framework (SRF) which we believe is the first method to adapt a CapsNet-only structure to sequence-to-sequence recognition. In SRF, input sequences are capsulized then sliced by the window size. Each sliced window is classified to a label at the corresponding time through iterative routing mechanisms. Afterwards, training losses are computed using connectionist temporal classification (CTC). During routing, two kinds of information, learnable weights and iteration outputs are shared across the slices. By sharing the information, the required parameter numbers can be controlled by the given window size regardless of the length of sequences. Moreover, the method can minimize decoding speed degradation caused by the routing iterations since it can operate in a non-iterative manner at inference time without dropping accuracy. We empirically proved the validity of our method by performing phoneme sequence recognition tasks on the TIMIT corpus. The proposed method attains an 82.6 of CNN-based CTC networks and on par with that of recurrent neural network transducers (RNN-Ts). Even more, the method requires less than half the parameters compared to the two architectures.

READ FULL TEXT

page 23

page 24

research
02/12/2020

Capsules with Inverted Dot-Product Attention Routing

We introduce a new routing algorithm for capsule networks, in which a ch...
research
07/19/2023

ProtoCaps: A Fast and Non-Iterative Capsule Network Routing Method

Capsule Networks have emerged as a powerful class of deep learning archi...
research
10/22/2018

Compositional coding capsule network with k-means routing for text classification

Text classification is a challenging problem which aims to identify the ...
research
10/28/2017

A Study of All-Convolutional Encoders for Connectionist Temporal Classification

Connectionist temporal classification (CTC) is a popular sequence predic...
research
11/01/2018

Towards Linear Time Neural Machine Translation with Capsule Networks

In this study, we first investigate a novel capsule network with dynamic...
research
06/05/2018

Information Aggregation via Dynamic Routing for Sequence Encoding

While much progress has been made in how to encode a text sequence into ...
research
10/11/2021

Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition

The visual system processes a scene using a sequence of selective glimps...

Please sign up or login with your details

Forgot password? Click here to reset