A Hybrid of Deep CNN and Bidirectional LSTM for Automatic Speech Recognition

A Hybrid of Deep CNN and Bidirectional LSTM for Automatic Speech Recognition

Deep neural networks (DNNs) have been playing a significant role in acoustic modeling. Convolutional neural networks (CNNs) are the advanced version of DNNs that achieve 4–12% relative gain in the word error rate (WER) over DNNs. Existence of spectral variations and local correlations in speech sign...

Full description

Bibliographic Details
Main Authors: Passricha Vishal, Aggarwal Rajesh Kumar
Format: Article
Language:English
Published: De Gruyter 2019-03-01
Series:Journal of Intelligent Systems
Subjects:
asr
cnn
cnn-blstm
dnn
lstm-rnn
Online Access:https://doi.org/10.1515/jisys-2018-0372

Internet

https://doi.org/10.1515/jisys-2018-0372

Similar Items