TELKOMNIKA Telecommunication, Computing, Electronics and Control
The convolutional neural networks for Amazigh speech recognition system
Dublin Core
Title
TELKOMNIKA Telecommunication, Computing, Electronics and Control
The convolutional neural networks for Amazigh speech recognition system
The convolutional neural networks for Amazigh speech recognition system
Subject
Amazigh language
Convolutional neural network
Deep learning
Mel frequency cepstral
coefficient
Spectrogram
Speech recognition
Convolutional neural network
Deep learning
Mel frequency cepstral
coefficient
Spectrogram
Speech recognition
Description
In this paper, we present an approach based on convolutional neural networks
to build an automatic speech recognition system for the Amazigh language.
This system is built with TensorFlow and uses mel frequency cepstral
coefficient (MFCC) to extract features. In order to test the effect of the
speaker's gender and age on the accuracy of the model, the system was trained
and tested on several datasets. The first experiment the dataset consists of 9240
audio files. The second experiment the dataset consists of 9240 audio files
distributed between females and males’ speakers. The last experiment 3 the
dataset consists of 13860 audio files distributed between age 9-15, age 16-30,
and age 30+. The result shows that the model trained on a dataset of adult
speaker’s age +30 categories generates the best accuracy with 93.9%.
to build an automatic speech recognition system for the Amazigh language.
This system is built with TensorFlow and uses mel frequency cepstral
coefficient (MFCC) to extract features. In order to test the effect of the
speaker's gender and age on the accuracy of the model, the system was trained
and tested on several datasets. The first experiment the dataset consists of 9240
audio files. The second experiment the dataset consists of 9240 audio files
distributed between females and males’ speakers. The last experiment 3 the
dataset consists of 13860 audio files distributed between age 9-15, age 16-30,
and age 30+. The result shows that the model trained on a dataset of adult
speaker’s age +30 categories generates the best accuracy with 93.9%.
Creator
Meryam Telmem, Youssef Ghanou
Source
http://journal.uad.ac.id/index.php/TELKOMNIKA
Date
Sep 24, 2020
Contributor
peri irawan
Format
pdf
Language
english
Type
text
Files
Collection
Citation
Meryam Telmem, Youssef Ghanou, “TELKOMNIKA Telecommunication, Computing, Electronics and Control
The convolutional neural networks for Amazigh speech recognition system,” Repository Horizon University Indonesia, accessed April 19, 2025, https://repository.horizon.ac.id/items/show/3703.
The convolutional neural networks for Amazigh speech recognition system,” Repository Horizon University Indonesia, accessed April 19, 2025, https://repository.horizon.ac.id/items/show/3703.