Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition

11/06/2018
by   Titouan Parcollet, et al.
0

Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition tasks, due to their efficient representation of long and short term dependencies in sequences of inter-dependent features. Nonetheless, internal dependencies within the element composing multidimensional features are weakly considered by traditional real-valued representations. We propose a novel quaternion long-short term memory (QLSTM) recurrent neural network that takes into account both the external relations between the features composing a sequence, and these internal latent structural dependencies with the quaternion algebra. QLSTMs are compared to LSTMs during a memory copy-task and a realistic application of speech recognition on the Wall Street Journal (WSJ) dataset. QLSTM reaches better performances during the two experiments with up to 2.8 times less learning parameters, leading to a more expressive representation of the information.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/18/2020

Quaternion Neural Networks for Multi-channel Distant Speech Recognition

Despite the significant progress in automatic speech recognition (ASR), ...
research
06/12/2018

Quaternion Recurrent Neural Networks

Recurrent neural networks (RNNs) are powerful architectures to model seq...
research
11/15/2017

Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition

Recurrent neural network (RNN) language models (LMs) and Long Short Term...
research
07/23/2018

Automatic Speech Recognition for Humanitarian Applications in Somali

We present our first efforts in building an automatic speech recognition...
research
10/30/2015

Highway Long Short-Term Memory RNNs for Distant Speech Recognition

In this paper, we extend the deep long short-term memory (DLSTM) recurre...
research
01/31/2021

Fine-tuning Handwriting Recognition systems with Temporal Dropout

This paper introduces a novel method to fine-tune handwriting recognitio...
research
08/04/2013

Generating Sequences With Recurrent Neural Networks

This paper shows how Long Short-term Memory recurrent neural networks ca...

Please sign up or login with your details

Forgot password? Click here to reset