Emotional speech-based personality prediction using NPSO architecture in deep learning
Speech is an effective way for analyzing mental and psychological health of a speaker's. Automatic speech recognition has been efficiently investigated for human-computer interaction and understanding the emotional & psychological anatomy of human behavior. Emotions and personality are...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-02-01
|
| Series: | Measurement: Sensors |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2665917422002896 |
| _version_ | 1811176059886895104 |
|---|---|
| author | Kalpana Rangra Virender Kadyan Monit Kapoor |
| author_facet | Kalpana Rangra Virender Kadyan Monit Kapoor |
| author_sort | Kalpana Rangra |
| collection | DOAJ |
| description | Speech is an effective way for analyzing mental and psychological health of a speaker's. Automatic speech recognition has been efficiently investigated for human-computer interaction and understanding the emotional & psychological anatomy of human behavior. Emotions and personality are studied to have a strong link while analyzing the prosodic speech parameters. The work proposes a novel personality and emotion classification model using PSO (particle swarm optimization) based CNN (convolution neural network): (NPSO) that predicts both (emotion and personality) The model is computationally efficient and outperforms language models. Cepstral speech features MFCC (mel frequency cepstral constants) is used to predict emotions with 90% testing accuracy and personality with 91% accuracy on SAVEE(Surrey Audio-Visual Expressed Emotion) individually. The correlation between emotion and personality is identified in the work. The experiment uses the four corpora SAVEE, RAVDESS (Ryerson Audio-Visual Database of Emotional Speech and Song), CREMAD (Crowd-sourced Emotional Multimodal Actors Dataset, TESS (Toronto emotional speech set) corpus, and the big five personality model for finding associations among emotions and personality traits. Experimental results show that the classification accuracy scores for combined datasets are 74% for emotions and 89% for Personality classifications. The proposed model works on seven emotions and five classes of personality. Results prove that MFCC is enough effective in characterizing and recognizing emotions and personality simultaneously. |
| first_indexed | 2024-04-10T19:46:59Z |
| format | Article |
| id | doaj.art-09d563d635924c3fa0dd6235712ae737 |
| institution | Directory Open Access Journal |
| issn | 2665-9174 |
| language | English |
| last_indexed | 2024-04-10T19:46:59Z |
| publishDate | 2023-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Measurement: Sensors |
| spelling | doaj.art-09d563d635924c3fa0dd6235712ae7372023-01-29T04:22:02ZengElsevierMeasurement: Sensors2665-91742023-02-0125100655Emotional speech-based personality prediction using NPSO architecture in deep learningKalpana Rangra0Virender Kadyan1Monit Kapoor2Speech and Language Research Centre (SLRC), University of Petroleum and Energy Studies, (UPES), Energy Acres, Bidholi, Deheradun, 248007, Uttrakhand, India; Corresponding authors.Speech and Language Research Centre (SLRC), University of Petroleum and Energy Studies, (UPES), Energy Acres, Bidholi, Deheradun, 248007, Uttrakhand, India; Corresponding authors.Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, IndiaSpeech is an effective way for analyzing mental and psychological health of a speaker's. Automatic speech recognition has been efficiently investigated for human-computer interaction and understanding the emotional & psychological anatomy of human behavior. Emotions and personality are studied to have a strong link while analyzing the prosodic speech parameters. The work proposes a novel personality and emotion classification model using PSO (particle swarm optimization) based CNN (convolution neural network): (NPSO) that predicts both (emotion and personality) The model is computationally efficient and outperforms language models. Cepstral speech features MFCC (mel frequency cepstral constants) is used to predict emotions with 90% testing accuracy and personality with 91% accuracy on SAVEE(Surrey Audio-Visual Expressed Emotion) individually. The correlation between emotion and personality is identified in the work. The experiment uses the four corpora SAVEE, RAVDESS (Ryerson Audio-Visual Database of Emotional Speech and Song), CREMAD (Crowd-sourced Emotional Multimodal Actors Dataset, TESS (Toronto emotional speech set) corpus, and the big five personality model for finding associations among emotions and personality traits. Experimental results show that the classification accuracy scores for combined datasets are 74% for emotions and 89% for Personality classifications. The proposed model works on seven emotions and five classes of personality. Results prove that MFCC is enough effective in characterizing and recognizing emotions and personality simultaneously.http://www.sciencedirect.com/science/article/pii/S2665917422002896Personality-classificationEmotion-classificationSpeech featuresMFCCPSOCNN |
| spellingShingle | Kalpana Rangra Virender Kadyan Monit Kapoor Emotional speech-based personality prediction using NPSO architecture in deep learning Measurement: Sensors Personality-classification Emotion-classification Speech features MFCC PSO CNN |
| title | Emotional speech-based personality prediction using NPSO architecture in deep learning |
| title_full | Emotional speech-based personality prediction using NPSO architecture in deep learning |
| title_fullStr | Emotional speech-based personality prediction using NPSO architecture in deep learning |
| title_full_unstemmed | Emotional speech-based personality prediction using NPSO architecture in deep learning |
| title_short | Emotional speech-based personality prediction using NPSO architecture in deep learning |
| title_sort | emotional speech based personality prediction using npso architecture in deep learning |
| topic | Personality-classification Emotion-classification Speech features MFCC PSO CNN |
| url | http://www.sciencedirect.com/science/article/pii/S2665917422002896 |
| work_keys_str_mv | AT kalpanarangra emotionalspeechbasedpersonalitypredictionusingnpsoarchitectureindeeplearning AT virenderkadyan emotionalspeechbasedpersonalitypredictionusingnpsoarchitectureindeeplearning AT monitkapoor emotionalspeechbasedpersonalitypredictionusingnpsoarchitectureindeeplearning |