CNN Based Automatic Speech Recognition: A Comparative Study
Recently, one of the most common approaches used in speech recognition is deep learning. The most advanced results have been obtained with speech recognition systems created using convolutional neural network (CNN) and recurrent neural networks (RNN). Since CNNs can capture local features effectivel...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ediciones Universidad de Salamanca
2024-08-01
|
| Series: | Advances in Distributed Computing and Artificial Intelligence Journal |
| Subjects: | |
| Online Access: | https://revistas.usal.es/cinco/index.php/2255-2863/article/view/29191 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590610190565376 |
|---|---|
| author | Hilal Ilgaz Beyza Akkoyun Özlem Alpay M. Ali Akcayol |
| author_facet | Hilal Ilgaz Beyza Akkoyun Özlem Alpay M. Ali Akcayol |
| author_sort | Hilal Ilgaz |
| collection | DOAJ |
| description | Recently, one of the most common approaches used in speech recognition is deep learning. The most advanced results have been obtained with speech recognition systems created using convolutional neural network (CNN) and recurrent neural networks (RNN). Since CNNs can capture local features effectively, they are applied to tasks with relatively short-term dependencies, such as keyword detection or phoneme- level sequence recognition. This paper presents the development of a deep learning and speech command recognition system. The Google Speech Commands Dataset has been used for training. The dataset contained 65.000 one-second-long words of 30 short English words. That is, %80 of the dataset has been used in the training and %20 of the dataset has been used in the testing. The data set consists of one-second voice commands that have been converted into a spectrogram and used to train different artificial neural network (ANN) models. Various variants of CNN are used in deep learning applications. The performance of the proposed model has reached %94.60. |
| format | Article |
| id | doaj-art-735a6efc68a0465f8100c3b93c74c2b8 |
| institution | Kabale University |
| issn | 2255-2863 |
| language | English |
| publishDate | 2024-08-01 |
| publisher | Ediciones Universidad de Salamanca |
| record_format | Article |
| series | Advances in Distributed Computing and Artificial Intelligence Journal |
| spelling | doaj-art-735a6efc68a0465f8100c3b93c74c2b82025-01-23T11:25:18ZengEdiciones Universidad de SalamancaAdvances in Distributed Computing and Artificial Intelligence Journal2255-28632024-08-0113e29191e2919110.14201/adcaij.2919134652CNN Based Automatic Speech Recognition: A Comparative StudyHilal Ilgaz0Beyza Akkoyun1Özlem Alpay2M. Ali Akcayol3Computer Engineering Department, University of Gazi. Ankara, TurkeyComputer Engineering Department, University of Gazi. Ankara, Turkey.Computer Engineering Department, University of Gazi. Ankara, Turkey.Computer Engineering Department, University of Gazi. Ankara, Turkey.Recently, one of the most common approaches used in speech recognition is deep learning. The most advanced results have been obtained with speech recognition systems created using convolutional neural network (CNN) and recurrent neural networks (RNN). Since CNNs can capture local features effectively, they are applied to tasks with relatively short-term dependencies, such as keyword detection or phoneme- level sequence recognition. This paper presents the development of a deep learning and speech command recognition system. The Google Speech Commands Dataset has been used for training. The dataset contained 65.000 one-second-long words of 30 short English words. That is, %80 of the dataset has been used in the training and %20 of the dataset has been used in the testing. The data set consists of one-second voice commands that have been converted into a spectrogram and used to train different artificial neural network (ANN) models. Various variants of CNN are used in deep learning applications. The performance of the proposed model has reached %94.60.https://revistas.usal.es/cinco/index.php/2255-2863/article/view/29191deep learningartificial neural networksspeech recognition |
| spellingShingle | Hilal Ilgaz Beyza Akkoyun Özlem Alpay M. Ali Akcayol CNN Based Automatic Speech Recognition: A Comparative Study Advances in Distributed Computing and Artificial Intelligence Journal deep learning artificial neural networks speech recognition |
| title | CNN Based Automatic Speech Recognition: A Comparative Study |
| title_full | CNN Based Automatic Speech Recognition: A Comparative Study |
| title_fullStr | CNN Based Automatic Speech Recognition: A Comparative Study |
| title_full_unstemmed | CNN Based Automatic Speech Recognition: A Comparative Study |
| title_short | CNN Based Automatic Speech Recognition: A Comparative Study |
| title_sort | cnn based automatic speech recognition a comparative study |
| topic | deep learning artificial neural networks speech recognition |
| url | https://revistas.usal.es/cinco/index.php/2255-2863/article/view/29191 |
| work_keys_str_mv | AT hilalilgaz cnnbasedautomaticspeechrecognitionacomparativestudy AT beyzaakkoyun cnnbasedautomaticspeechrecognitionacomparativestudy AT ozlemalpay cnnbasedautomaticspeechrecognitionacomparativestudy AT maliakcayol cnnbasedautomaticspeechrecognitionacomparativestudy |