Multimodal emotion recognition from Speech and text using heterogeneous ensemble techniques
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022.
| Κύριοι συγγραφείς: | , , , |
|---|---|
| Άλλοι συγγραφείς: | |
| Μορφή: | Thesis |
| Γλώσσα: | en_US |
| Έκδοση: |
Brac University
2022
|
| Θέματα: | |
| Διαθέσιμο Online: | http://hdl.handle.net/10361/17613 |
| id |
10361-17613 |
|---|---|
| record_format |
dspace |
| spelling |
10361-176132022-11-23T21:01:43Z Multimodal emotion recognition from Speech and text using heterogeneous ensemble techniques Rafidul Islam, Sheikh Md Gomes, Maria Hossain, Mehran Raihana, Ramisha Esfar-E-Alam, A. M. Monim, Mobashir Department of Computer Science and Engineering, Brac University Multimodal Ensemble learning Emotion recognition Speech Text Stacking IEMOCAP Emotions--Computer simulation Emotions -- Computer simulation. This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (pages 29-30). Emotion recognition and sentiment analysis serves many purposes from analyzing human behavior under specific conditions to enhancement of customer experience for various services. In this paper, a multimodal approach is used to identify 4 classes of emotions by combining both speech and text features to improve classification accuracy. The methodology involves the implementation of several models for both audio and text domains combined using 4 different heterogeneous ensemble tech niques - hard voting, soft voting, blending and stacking. The effects of the different ensemble learning methods on the accuracy for the multimodal classification task are also investigated. The results of this study show that stacking is the highest performing ensemble technique, and the implementation outperforms several exist ing methods for 4-class emotion detection on the IEMOCAP dataset, obtaining a weighted accuracy of 81.2%. Sheikh Md Rafidul Islam Maria Gomes Mehran Hossain Ramisha Raihana B. Computer Science 2022-11-23T06:16:38Z 2022-11-23T06:16:38Z 2022 2022-05 Thesis ID: 22141059 ID: 22141070 ID: 22141043 ID: 21241077 http://hdl.handle.net/10361/17613 en_US Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 30 Pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
en_US |
| topic |
Multimodal Ensemble learning Emotion recognition Speech Text Stacking IEMOCAP Emotions--Computer simulation Emotions -- Computer simulation. |
| spellingShingle |
Multimodal Ensemble learning Emotion recognition Speech Text Stacking IEMOCAP Emotions--Computer simulation Emotions -- Computer simulation. Rafidul Islam, Sheikh Md Gomes, Maria Hossain, Mehran Raihana, Ramisha Multimodal emotion recognition from Speech and text using heterogeneous ensemble techniques |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022. |
| author2 |
Esfar-E-Alam, A. M. |
| author_facet |
Esfar-E-Alam, A. M. Rafidul Islam, Sheikh Md Gomes, Maria Hossain, Mehran Raihana, Ramisha |
| format |
Thesis |
| author |
Rafidul Islam, Sheikh Md Gomes, Maria Hossain, Mehran Raihana, Ramisha |
| author_sort |
Rafidul Islam, Sheikh Md |
| title |
Multimodal emotion recognition from Speech and text using heterogeneous ensemble techniques |
| title_short |
Multimodal emotion recognition from Speech and text using heterogeneous ensemble techniques |
| title_full |
Multimodal emotion recognition from Speech and text using heterogeneous ensemble techniques |
| title_fullStr |
Multimodal emotion recognition from Speech and text using heterogeneous ensemble techniques |
| title_full_unstemmed |
Multimodal emotion recognition from Speech and text using heterogeneous ensemble techniques |
| title_sort |
multimodal emotion recognition from speech and text using heterogeneous ensemble techniques |
| publisher |
Brac University |
| publishDate |
2022 |
| url |
http://hdl.handle.net/10361/17613 |
| work_keys_str_mv |
AT rafidulislamsheikhmd multimodalemotionrecognitionfromspeechandtextusingheterogeneousensembletechniques AT gomesmaria multimodalemotionrecognitionfromspeechandtextusingheterogeneousensembletechniques AT hossainmehran multimodalemotionrecognitionfromspeechandtextusingheterogeneousensembletechniques AT raihanaramisha multimodalemotionrecognitionfromspeechandtextusingheterogeneousensembletechniques |
| _version_ |
1814308898682699776 |