Deep Bidirectional RNNs Using Gated Recurrent Units and Long Short-Term Memory Units for Building Acoustic Models for Automatic Speech Recognition
Published: 2019
Author(s) Name: Madhuri Jain, Nishita Dutta, Dnyaneshwari Bhirud and Nikahat Mulla |
Author(s) Affiliation: Sardar Patel Institute of Technology, Andheri, Mumbai, Maharashtra, India.
Locked
Subscribed
Available for All
Abstract
Deep Neural Networks are gaining popularity to train speech dataset for speech recognition. A lot of work has been done with various neural network models, starting right from conventional convolutional neural networks to deep recurrent neural networks. Research has led us to arrive at the conclusion that bidirectional RNNs are suited for speech recognition. It has been seen that bidirectional RNNs provide greater accuracy as compared to deep RNNs and unidirectional RNNs. Units that are used with bidirectional RNNs are usually Long Short-Term Memory units. They have their own advantages and disadvantages. Gated Recurrent Units can also be used. In this paper we have tried to experiment and compare between deep bidirectional models using GRU units and LSTM units.
Keywords: Acoustic modeling, Automatic speech recognition, Bidirectional RNN, Convolutional neural networks, Deep recurrent neural networks, Gated recurrent unit, Keras, Long Short-Term Memory (LSTM), MFCC.
View PDF