Ensemble Learning of Hybrid Acoustic Features for Speech Emotion Recognition
Automatic recognition of emotion is important for facilitating seamless interactivity between a human being and intelligent robot towards the full realization of a smart society. The methods of signal processing and machine learning are widely applied to recognize human emotions based on features ex...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/13/3/70 |
| _version_ | 1828860209389371392 |
|---|---|
| author | Kudakwashe Zvarevashe Oludayo Olugbara |
| author_facet | Kudakwashe Zvarevashe Oludayo Olugbara |
| author_sort | Kudakwashe Zvarevashe |
| collection | DOAJ |
| description | Automatic recognition of emotion is important for facilitating seamless interactivity between a human being and intelligent robot towards the full realization of a smart society. The methods of signal processing and machine learning are widely applied to recognize human emotions based on features extracted from facial images, video files or speech signals. However, these features were not able to recognize the fear emotion with the same level of precision as other emotions. The authors propose the agglutination of prosodic and spectral features from a group of carefully selected features to realize hybrid acoustic features for improving the task of emotion recognition. Experiments were performed to test the effectiveness of the proposed features extracted from speech files of two public databases and used to train five popular ensemble learning algorithms. Results show that random decision forest ensemble learning of the proposed hybrid acoustic features is highly effective for speech emotion recognition. |
| first_indexed | 2024-12-13T02:33:37Z |
| format | Article |
| id | doaj.art-49380c27ac1a461fa95e260cca1305e4 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-12-13T02:33:37Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-49380c27ac1a461fa95e260cca1305e42022-12-22T00:02:26ZengMDPI AGAlgorithms1999-48932020-03-011337010.3390/a13030070a13030070Ensemble Learning of Hybrid Acoustic Features for Speech Emotion RecognitionKudakwashe Zvarevashe0Oludayo Olugbara1ICT and Society Research Group, South Africa Luban Workshop, Durban University of Technology, Durban 4001, South AfricaICT and Society Research Group, South Africa Luban Workshop, Durban University of Technology, Durban 4001, South AfricaAutomatic recognition of emotion is important for facilitating seamless interactivity between a human being and intelligent robot towards the full realization of a smart society. The methods of signal processing and machine learning are widely applied to recognize human emotions based on features extracted from facial images, video files or speech signals. However, these features were not able to recognize the fear emotion with the same level of precision as other emotions. The authors propose the agglutination of prosodic and spectral features from a group of carefully selected features to realize hybrid acoustic features for improving the task of emotion recognition. Experiments were performed to test the effectiveness of the proposed features extracted from speech files of two public databases and used to train five popular ensemble learning algorithms. Results show that random decision forest ensemble learning of the proposed hybrid acoustic features is highly effective for speech emotion recognition.https://www.mdpi.com/1999-4893/13/3/70emotion recognitionensemble algorithmfeature extractionhybrid featuremachine learningsupervised learning |
| spellingShingle | Kudakwashe Zvarevashe Oludayo Olugbara Ensemble Learning of Hybrid Acoustic Features for Speech Emotion Recognition Algorithms emotion recognition ensemble algorithm feature extraction hybrid feature machine learning supervised learning |
| title | Ensemble Learning of Hybrid Acoustic Features for Speech Emotion Recognition |
| title_full | Ensemble Learning of Hybrid Acoustic Features for Speech Emotion Recognition |
| title_fullStr | Ensemble Learning of Hybrid Acoustic Features for Speech Emotion Recognition |
| title_full_unstemmed | Ensemble Learning of Hybrid Acoustic Features for Speech Emotion Recognition |
| title_short | Ensemble Learning of Hybrid Acoustic Features for Speech Emotion Recognition |
| title_sort | ensemble learning of hybrid acoustic features for speech emotion recognition |
| topic | emotion recognition ensemble algorithm feature extraction hybrid feature machine learning supervised learning |
| url | https://www.mdpi.com/1999-4893/13/3/70 |
| work_keys_str_mv | AT kudakwashezvarevashe ensemblelearningofhybridacousticfeaturesforspeechemotionrecognition AT oludayoolugbara ensemblelearningofhybridacousticfeaturesforspeechemotionrecognition |