Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition
Speech emotion recognition (SER) systems have evolved into an important method for recognizing a person in several applications, including e-commerce, everyday interactions, law enforcement, and forensics. The SER system’s efficiency depends on the length of the audio samples used for testing and tr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2022-08-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1053.pdf |
| _version_ | 1798038665018998784 |
|---|---|
| author | Ammar Amjad Lal Khan Hsien-Tsung Chang |
| author_facet | Ammar Amjad Lal Khan Hsien-Tsung Chang |
| author_sort | Ammar Amjad |
| collection | DOAJ |
| description | Speech emotion recognition (SER) systems have evolved into an important method for recognizing a person in several applications, including e-commerce, everyday interactions, law enforcement, and forensics. The SER system’s efficiency depends on the length of the audio samples used for testing and training. However, the different suggested models successfully obtained relatively high accuracy in this study. Moreover, the degree of SER efficiency is not yet optimum due to the limited database, resulting in overfitting and skewing samples. Therefore, the proposed approach presents a data augmentation method that shifts the pitch, uses multiple window sizes, stretches the time, and adds white noise to the original audio. In addition, a deep model is further evaluated to generate a new paradigm for SER. The data augmentation approach increased the limited amount of data from the Pakistani racial speaker speech dataset in the proposed system. The seven-layer framework was employed to provide the most optimal performance in terms of accuracy compared to other multilayer approaches. The seven-layer method is used in existing works to achieve a very high level of accuracy. The suggested system achieved 97.32% accuracy with a 0.032% loss in the 75%:25% splitting ratio. In addition, more than 500 augmentation data samples were added. Therefore, the proposed approach results show that deep neural networks with data augmentation can enhance the SER performance on the Pakistani racial speech dataset. |
| first_indexed | 2024-04-11T21:43:13Z |
| format | Article |
| id | doaj.art-93130679fa304b1d99f4a7f000949ad1 |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-04-11T21:43:13Z |
| publishDate | 2022-08-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-93130679fa304b1d99f4a7f000949ad12022-12-22T04:01:30ZengPeerJ Inc.PeerJ Computer Science2376-59922022-08-018e105310.7717/peerj-cs.1053Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognitionAmmar Amjad0Lal Khan1Hsien-Tsung Chang2Department of Computer Science and Information Engineering, Chang Gung University, Taoyuan, TaiwanDepartment of Computer Science and Information Engineering, Chang Gung University, Taoyuan, TaiwanDepartment of Computer Science and Information Engineering, Chang Gung University, Taoyuan, TaiwanSpeech emotion recognition (SER) systems have evolved into an important method for recognizing a person in several applications, including e-commerce, everyday interactions, law enforcement, and forensics. The SER system’s efficiency depends on the length of the audio samples used for testing and training. However, the different suggested models successfully obtained relatively high accuracy in this study. Moreover, the degree of SER efficiency is not yet optimum due to the limited database, resulting in overfitting and skewing samples. Therefore, the proposed approach presents a data augmentation method that shifts the pitch, uses multiple window sizes, stretches the time, and adds white noise to the original audio. In addition, a deep model is further evaluated to generate a new paradigm for SER. The data augmentation approach increased the limited amount of data from the Pakistani racial speaker speech dataset in the proposed system. The seven-layer framework was employed to provide the most optimal performance in terms of accuracy compared to other multilayer approaches. The seven-layer method is used in existing works to achieve a very high level of accuracy. The suggested system achieved 97.32% accuracy with a 0.032% loss in the 75%:25% splitting ratio. In addition, more than 500 augmentation data samples were added. Therefore, the proposed approach results show that deep neural networks with data augmentation can enhance the SER performance on the Pakistani racial speech dataset.https://peerj.com/articles/cs-1053.pdfSpeaker recognitionData augmentationDeep neural networkMultiple window size |
| spellingShingle | Ammar Amjad Lal Khan Hsien-Tsung Chang Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition PeerJ Computer Science Speaker recognition Data augmentation Deep neural network Multiple window size |
| title | Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition |
| title_full | Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition |
| title_fullStr | Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition |
| title_full_unstemmed | Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition |
| title_short | Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition |
| title_sort | data augmentation and deep neural networks for the classification of pakistani racial speakers recognition |
| topic | Speaker recognition Data augmentation Deep neural network Multiple window size |
| url | https://peerj.com/articles/cs-1053.pdf |
| work_keys_str_mv | AT ammaramjad dataaugmentationanddeepneuralnetworksfortheclassificationofpakistaniracialspeakersrecognition AT lalkhan dataaugmentationanddeepneuralnetworksfortheclassificationofpakistaniracialspeakersrecognition AT hsientsungchang dataaugmentationanddeepneuralnetworksfortheclassificationofpakistaniracialspeakersrecognition |