Speech recognition based on convolutional neural networks and MFCC algorithm

Arzo MAHMOOD; Utku KÖSE

Makale detayları

Speech recognition based on convolutional neural networks and MFCC algorithm

Yazarlar:

Arzo MAHMOOD | Utku KÖSE

Yayıncı:

Osman ÖZKARACA

Ana Başlıklar:

Özel bilgisayar yöntemleri

Dergi:

Advances in Artificial Intelligence Research 2021 Vol.1 Issue 1, pp.6-12

Belge Tipi:

Makale

Yayın Tarihi:

1/2021

Belge Dili:

İngilizce

Document ID (Org No.):

2000447264

Sıklık:

İki Yıllık

pISSN:

2757-7422

Özet:

 

In this paper, an automatic speech recognition system based on convolutional neural networks and MFCC has been proposed. We have been investigated some deep models’ architecture with various hyperparameters options such as Dropout rate and Learning rate. The dataset used in this paper was collected from Kaggle TensorFlow Speech Recognition Challenge. Each audio file in the dataset contain one word with one second length the total words in the dataset correspond to 30 categories with one category for background noise. The dataset contains 64,721 files has been separated into 51,088 for the training set, 6,798 for the validation set and 6,835 for the testing set. We have evaluated 3 models with different hyperparameters configuration in order to choose the best model with higher accuracy. The highest accuracy achieved is 88.21%.

Makale detayları

Speech recognition based on convolutional neural networks and MFCC algorithm

Yazarlar: Arzo MAHMOOD | Utku KÖSE

Yayıncı: Osman ÖZKARACA

Ana Başlıklar: Özel bilgisayar yöntemleri

Dergi: Advances in Artificial Intelligence Research 2021 Vol.1 Issue 1, pp.6-12

Belge Tipi: Makale

Yayın Tarihi: 1/2021

Belge Dili: İngilizce

Document ID (Org No.): 2000447264

Sıklık: İki Yıllık

pISSN: 2757-7422

Sayı

Yazarlar:

Arzo MAHMOOD | Utku KÖSE

Yayıncı:

Osman ÖZKARACA

Ana Başlıklar:

Özel bilgisayar yöntemleri

Dergi:

Advances in Artificial Intelligence Research 2021 Vol.1 Issue 1, pp.6-12

Belge Tipi:

Makale

Yayın Tarihi:

1/2021

Belge Dili:

İngilizce

Document ID (Org No.):

2000447264

Sıklık:

İki Yıllık

pISSN:

2757-7422