Article

Image Approach to Speech Recognition on CNN

Muhammadjon MusaevComputer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, UzbekistanIlyos KhujayorovComputer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, UzbekistanMannon OchilovComputer Systems, Tashkent University of Information technologies named after, Muhammad Al-Khwarizmi, Tashkent, Uzbekistan

2019en

ABI

Abstract

In this paper has been discussed about speech recognition using spectrogram images and deep convolution neural network(CNN) of Uzbek spoken digits. Spectrogram images from speech signal were generated and it were used for deep CNN training. Presented CNN model contains 3 convolution layers and 2 fully connected layers that discriminative features can be divided and estimated of spectrogram images by those layers. In current research period, dataset of Uzbek spoken digits were made and in based on presented CNN model they were trained. Testing results shows that, proposed approach for Uzbek spoken digits classified 100% accuracy.

Topics

Speech and Audio Processing Speech Recognition and Synthesis Music and Audio Processing

Identifiers

DOI: 10.1145/3386164.3389100

Citations and references

Cited by 16 25 references

Metrics — AkademScholar · Coming soon