Foreign accent classification using deep neural nets

Issue title: Special section: Soft Computing and Intelligent Systems: Techniques and Applications

Guest editors: Sabu M. Thampi, El-Sayed M. El-Alfy and Ljiljana Trajkovic

Article type: Research Article

Authors: Singh, Utkarsh^{a; *} | Gupta, Akshay^b | Bisharad, Dipjyoti^c | Arif, Wasim^c

Affiliations: [a] Computer Science and Engineering, National Institute of Technology Silchar, Silchar, India | [b] Electronics and Instrumentation Engineering, National Institute of Technology Silchar, Silchar, India | [c] Electronics and Communication Engineering, National Institute of Technology Silchar, Silchar, India

Correspondence: [*] Corresponding author. Utkarsh Singh, Computer Science and Engineering, National Institute of Technology Silchar, Silchar, India. E-mail: 98singhutkarsh@gmail.com.

Abstract: Speech analysis for extracting attributes such as the speaker, gender, accent and like has been a field of great interest and has been widely studied. The paper presents a novel architecture for accent identification by using a cascade of two deep-learning architecture. We design and test our proposed architecture on common voice dataset. The architecture consists of a cascade of Convolutional Neural Network (CNN) and Convolutional Recurrent Neural Network (CRNN). It is trained on Mel-spectrogram of the audios. We consider five of the most popular English accents groups namely India, Australia, US, England, Canada in this study. The proposed model has an accuracy of 78.48% using CNN and 83.21% using CRNN.

Keywords: Mel-spectrogram, deep neural networks, foreign accent classification, recurrent neural network

DOI: 10.3233/JIFS-179715

Journal: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 5, pp. 6347-6352, 2020