Research Area: Machine Learning
The performance of speech recognition tasks utilizing systems based on deep learning has improved dramatically in recent years by utilizing different deep designs and learning methodologies. A popular way to boosting the number of training data is called Data Augmentation (DA), and research shows that using DA is effective in teaching neural network models how to make invariant predictions. furthermore, EM approaches have piqued machine-learning researchers attention as a means of improving classifier performance. In this study, have been presenteded a unique deep neural network speech recognition that employs both EM and DA approaches to improve the systems prediction accuracy. firstly, reveal an approach based on vocal tract length disturbance that already exists and then propose a Feature perturbation is an alternative Data Augmentation approach. in order to make amendment training data sets. This is followed by an integration of the posterior probabilities obtained from several DNN acoustic models trained on diverse datasets. The studys findings reveal that the proposed systems recognition skills have improved.
Keywords:
Automatic Speech Recognition
Deep Neural Networks
Data Augmentation
Deep Learning
Machine Learning
Author(s) Name: Muhammad D. Hassan, Ali Nejdet Nasret, Mohammed Rashad Baker, Zuhair Shakor Mahmood
Journal name: Hassan
Conferrence name:
Publisher name: PEN
DOI: 10.21533/pen.v9i4.2450
Volume Information: Vol 9, No 4 (2021)
