Abstract

Artificial intelligence (AI), particularly machine learning (ML) and neural networks (NN), has various applications and has sparked a lot of interest in the recent years due to its superior performance in a variety of tasks. Automatic speech recognition (ASR) is a technique that is becoming more important with the passage of time and is being used in our daily lives. Speech recognition is an important application of ML and NN, which is the auditory system of machines that realize the communication between humans and machines. In general, speech recognition methods are divided into three types, i.e., based on the channel model and speech knowledge method, template matching scheme, and the use of NN method. The main problem associated with the existing speech recognition methods is the low recognition accuracy and more computation time. In order to overcome the problem of low recognition accuracy of existing speech recognition techniques, a speech recognition technology based on the combination of deep convolution neural network (DCNN) algorithm and transfer learning techniques, i.e., VGG-16, is proposed in this study. Due to the limited application range of DCNN, when the input and output parameters are changed, it is necessary to reconstruct the model that leads to a long training time of the architecture. Therefore, the migration learning method is conducive to reducing the size of the dataset. Various experiments have been performed using different dataset constructs. The simulation results show that transfer learning is not only suitable for the comparison between the source dataset and the target dataset, but also suitable for two different datasets. The application of small datasets not only reduces the time and cost of dataset generation, but also reduces the training time and the requirement of computing power. From the experimental results, it is quite obvious that the proposed system performed better than the existing speech recognition methods, and its performance is superior in terms of recognition accuracy than the other approaches.

Highlights

  • Hearing loss affects an estimated 360–362 million individuals worldwide [1]. ese figures are anticipated to grow by 40% on average by the year 2035

  • Is study uses deep learning (DL) and transfer learning techniques for speech recognition. e primary contributions of this study are given as follows: (i) is paper proposes a method by combining deep convolution neural network (DCNN) algorithm with transfer learning to realize the speech recognition

  • Automatic speech recognition (ASR) is a technique that is becoming more important with the passage of time and is being used in our daily lives. is paper mainly uses the combination of DCNN and transfer learning techniques, i.e., VGG-16, for speech recognition. e main goal of this study is to use transfer learning techniques for the speech recognition and to increase the recognition accuracy of audio speech files

Read more

Summary

Hexue Shen

College of Music, Chongqing Arts and Sciences University, Chongqing 440000, China. Received 19 July 2021; Revised 6 September 2021; Accepted 22 September 2021; Published 11 October 2021. Artificial intelligence (AI), machine learning (ML) and neural networks (NN), has various applications and has sparked a lot of interest in the recent years due to its superior performance in a variety of tasks. E main problem associated with the existing speech recognition methods is the low recognition accuracy and more computation time. In order to overcome the problem of low recognition accuracy of existing speech recognition techniques, a speech recognition technology based on the combination of deep convolution neural network (DCNN) algorithm and transfer learning techniques, i.e., VGG-16, is proposed in this study. It is quite obvious that the proposed system performed better than the existing speech recognition methods, and its performance is superior in terms of recognition accuracy than the other approaches

Introduction
Related Work
Fully connected layer Flattening layer
Female sex
Class hours
Findings
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call