Early threat warning via speech and emotion recognition from voice calls
This thesis is submitted in partial fulfilment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2018.
| Huvudupphovsmän: | , , |
|---|---|
| Övriga upphovsmän: | |
| Materialtyp: | Lärdomsprov |
| Språk: | English |
| Publicerad: |
BRAC University
2019
|
| Ämnen: | |
| Länkar: | http://hdl.handle.net/10361/11412 |
| id |
10361-11412 |
|---|---|
| record_format |
dspace |
| spelling |
10361-114122022-01-26T10:08:18Z Early threat warning via speech and emotion recognition from voice calls Ishtiak, Ifaz Rahman, Mohammad Mazedur Usmani, Md.Razaul Haque Arif, Hossain Department of Computer Science and Engineering, BRAC University Emotion recognition Vector machines Speech to Text Random forest Feature extraction MFCC Human-computer interaction. Artificial intelligence. Emotions -- Computer simulation. This thesis is submitted in partial fulfilment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2018. Includes bibliographical references (pages 53-56). Cataloged from PDF version of thesis. The aim of this system is to identify potential cases of threats, and provide an early warning or alert to such cases. This will be based on voice such as voice chat over telecommunication networks or social media. The intended result will be achieved in three major steps. At first, the conversion of speech to text from both real time audio recordings and from accent groups will be applied using primarily IBM Watson’s Speech to Text. This will then be used to identify possible trigger words or word patterns from a classified selection of threat-related and negative words. And finally, the same audio source will be utilized for detecting emotions from the frequency shifts through vocal feature extraction from audio input and processing it using multiple classifier algorithms such as Support Vector Machines (SVMs), Random Forests and Naïve Bayes. Libraries such as LibROSA will be applied to extract primary audio features such as Mel Frequency Cepstral Coefficients (MFCC) to generate accurate predictions. The system yields a result of approximately 84% using the SVM RBF (Radial Basis Function) kernel, which highlights the accuracy of emotion detected based on the speech. Keywords— Emotion Recognition; Support Vector Machines; Speech to Text; Random Forest; Feature Extraction; MFCC Ifaz Ishtiak Rahman, Mohammad Mazedur Md.Razaul Haque Usmani B. Computer Science and Engineering 2019-02-14T05:37:49Z 2019-02-14T05:37:49Z 2018 2018-12 Thesis ID 15101118 ID 15101043 ID 14241005 http://hdl.handle.net/10361/11412 en 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. 63 pages application/pdf BRAC University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Emotion recognition Vector machines Speech to Text Random forest Feature extraction MFCC Human-computer interaction. Artificial intelligence. Emotions -- Computer simulation. |
| spellingShingle |
Emotion recognition Vector machines Speech to Text Random forest Feature extraction MFCC Human-computer interaction. Artificial intelligence. Emotions -- Computer simulation. Ishtiak, Ifaz Rahman, Mohammad Mazedur Usmani, Md.Razaul Haque Early threat warning via speech and emotion recognition from voice calls |
| description |
This thesis is submitted in partial fulfilment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2018. |
| author2 |
Arif, Hossain |
| author_facet |
Arif, Hossain Ishtiak, Ifaz Rahman, Mohammad Mazedur Usmani, Md.Razaul Haque |
| format |
Thesis |
| author |
Ishtiak, Ifaz Rahman, Mohammad Mazedur Usmani, Md.Razaul Haque |
| author_sort |
Ishtiak, Ifaz |
| title |
Early threat warning via speech and emotion recognition from voice calls |
| title_short |
Early threat warning via speech and emotion recognition from voice calls |
| title_full |
Early threat warning via speech and emotion recognition from voice calls |
| title_fullStr |
Early threat warning via speech and emotion recognition from voice calls |
| title_full_unstemmed |
Early threat warning via speech and emotion recognition from voice calls |
| title_sort |
early threat warning via speech and emotion recognition from voice calls |
| publisher |
BRAC University |
| publishDate |
2019 |
| url |
http://hdl.handle.net/10361/11412 |
| work_keys_str_mv |
AT ishtiakifaz earlythreatwarningviaspeechandemotionrecognitionfromvoicecalls AT rahmanmohammadmazedur earlythreatwarningviaspeechandemotionrecognitionfromvoicecalls AT usmanimdrazaulhaque earlythreatwarningviaspeechandemotionrecognitionfromvoicecalls |
| _version_ |
1814307255869243392 |