Open Access iconOpen Access

ARTICLE

crossmark

An Innovative Approach Utilizing Binary-View Transformer for Speech Recognition Task

Muhammad Babar Kamal1, Arfat Ahmad Khan2, Faizan Ahmed Khan3, Malik Muhammad Ali Shahid4, Chitapong Wechtaisong2,*, Muhammad Daud Kamal5, Muhammad Junaid Ali6, Peerapong Uthansakul2

1 COMSATS University Islamabad, Islamabad Campus, 45550, Pakistan
2 Suranaree University of Technology, Nakhon Ratchasima, 30000, Thailand
3 COMSATS University Islamabad, Lahore Campus, 54000, Pakistan
4 COMSATS University Islamabad, Vehari Campus, 61100, Pakistan
5 National University of Sciences & Technology, Islamabad, 45550, Pakistan
6 Virtual University of Pakistan, Islamabad Campus, 45550, Pakistan

* Corresponding Author: Chitapong Wechtaisong. Email: email

Computers, Materials & Continua 2022, 72(3), 5547-5562. https://doi.org/10.32604/cmc.2022.024590

Abstract

The deep learning advancements have greatly improved the performance of speech recognition systems, and most recent systems are based on the Recurrent Neural Network (RNN). Overall, the RNN works fine with the small sequence data, but suffers from the gradient vanishing problem in case of large sequence. The transformer networks have neutralized this issue and have shown state-of-the-art results on sequential or speech-related data. Generally, in speech recognition, the input audio is converted into an image using Mel-spectrogram to illustrate frequencies and intensities. The image is classified by the machine learning mechanism to generate a classification transcript. However, the audio frequency in the image has low resolution and causing inaccurate predictions. This paper presents a novel end-to-end binary view transformer-based architecture for speech recognition to cope with the frequency resolution problem. Firstly, the input audio signal is transformed into a 2D image using Mel-spectrogram. Secondly, the modified universal transformers utilize the multi-head attention to derive contextual information and derive different speech-related features. Moreover, a feed-forward neural network is also deployed for classification. The proposed system has generated robust results on Google's speech command dataset with an accuracy of 95.16% and with minimal loss. The binary-view transformer eradicates the eventuality of the over-fitting problem by deploying a multi-view mechanism to diversify the input data, and multi-head attention captures multiple contexts from the data's feature map.

Keywords


Cite This Article

APA Style
Kamal, M.B., Khan, A.A., Khan, F.A., Shahid, M.M.A., Wechtaisong, C. et al. (2022). An innovative approach utilizing binary-view transformer for speech recognition task. Computers, Materials & Continua, 72(3), 5547-5562. https://doi.org/10.32604/cmc.2022.024590
Vancouver Style
Kamal MB, Khan AA, Khan FA, Shahid MMA, Wechtaisong C, Kamal MD, et al. An innovative approach utilizing binary-view transformer for speech recognition task. Comput Mater Contin. 2022;72(3):5547-5562 https://doi.org/10.32604/cmc.2022.024590
IEEE Style
M.B. Kamal et al., "An Innovative Approach Utilizing Binary-View Transformer for Speech Recognition Task," Comput. Mater. Contin., vol. 72, no. 3, pp. 5547-5562. 2022. https://doi.org/10.32604/cmc.2022.024590



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1359

    View

  • 792

    Download

  • 0

    Like

Share Link