Speech emotion classification using attention based network and regularized feature selection
Abstract Speech emotion classification (SEC) has gained the utmost height and occupied a conspicuous position within the research community in recent times. Its vital role in Human–Computer Interaction (HCI) and affective computing cannot be overemphasized. Many primitive algorithmic solutions and d...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-38868-2 |
| _version_ | 1797769497308823552 |
|---|---|
| author | Samson Akinpelu Serestina Viriri |
| author_facet | Samson Akinpelu Serestina Viriri |
| author_sort | Samson Akinpelu |
| collection | DOAJ |
| description | Abstract Speech emotion classification (SEC) has gained the utmost height and occupied a conspicuous position within the research community in recent times. Its vital role in Human–Computer Interaction (HCI) and affective computing cannot be overemphasized. Many primitive algorithmic solutions and deep neural network (DNN) models have been proposed for efficient recognition of emotion from speech however, the suitability of these methods to accurately classify emotion from speech with multi-lingual background and other factors that impede efficient classification of emotion is still demanding critical consideration. This study proposed an attention-based network with a pre-trained convolutional neural network and regularized neighbourhood component analysis (RNCA) feature selection techniques for improved classification of speech emotion. The attention model has proven to be successful in many sequence-based and time-series tasks. An extensive experiment was carried out using three major classifiers (SVM, MLP and Random Forest) on a publicly available TESS (Toronto English Speech Sentence) dataset. The result of our proposed model (Attention-based DCNN+RNCA+RF) achieved 97.8% classification accuracy and yielded a 3.27% improved performance, which outperforms state-of-the-art SEC approaches. Our model evaluation revealed the consistency of attention mechanism and feature selection with human behavioural patterns in classifying emotion from auditory speech. |
| first_indexed | 2024-03-12T21:09:56Z |
| format | Article |
| id | doaj.art-4b29b0028f994e7dbb52c651c22ffbf3 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-12T21:09:56Z |
| publishDate | 2023-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-4b29b0028f994e7dbb52c651c22ffbf32023-07-30T11:13:56ZengNature PortfolioScientific Reports2045-23222023-07-0113111410.1038/s41598-023-38868-2Speech emotion classification using attention based network and regularized feature selectionSamson Akinpelu0Serestina Viriri1School of Mathematics, Statistics and Computer Science, University of KwaZulu-NatalSchool of Mathematics, Statistics and Computer Science, University of KwaZulu-NatalAbstract Speech emotion classification (SEC) has gained the utmost height and occupied a conspicuous position within the research community in recent times. Its vital role in Human–Computer Interaction (HCI) and affective computing cannot be overemphasized. Many primitive algorithmic solutions and deep neural network (DNN) models have been proposed for efficient recognition of emotion from speech however, the suitability of these methods to accurately classify emotion from speech with multi-lingual background and other factors that impede efficient classification of emotion is still demanding critical consideration. This study proposed an attention-based network with a pre-trained convolutional neural network and regularized neighbourhood component analysis (RNCA) feature selection techniques for improved classification of speech emotion. The attention model has proven to be successful in many sequence-based and time-series tasks. An extensive experiment was carried out using three major classifiers (SVM, MLP and Random Forest) on a publicly available TESS (Toronto English Speech Sentence) dataset. The result of our proposed model (Attention-based DCNN+RNCA+RF) achieved 97.8% classification accuracy and yielded a 3.27% improved performance, which outperforms state-of-the-art SEC approaches. Our model evaluation revealed the consistency of attention mechanism and feature selection with human behavioural patterns in classifying emotion from auditory speech.https://doi.org/10.1038/s41598-023-38868-2 |
| spellingShingle | Samson Akinpelu Serestina Viriri Speech emotion classification using attention based network and regularized feature selection Scientific Reports |
| title | Speech emotion classification using attention based network and regularized feature selection |
| title_full | Speech emotion classification using attention based network and regularized feature selection |
| title_fullStr | Speech emotion classification using attention based network and regularized feature selection |
| title_full_unstemmed | Speech emotion classification using attention based network and regularized feature selection |
| title_short | Speech emotion classification using attention based network and regularized feature selection |
| title_sort | speech emotion classification using attention based network and regularized feature selection |
| url | https://doi.org/10.1038/s41598-023-38868-2 |
| work_keys_str_mv | AT samsonakinpelu speechemotionclassificationusingattentionbasednetworkandregularizedfeatureselection AT serestinaviriri speechemotionclassificationusingattentionbasednetworkandregularizedfeatureselection |