IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Extraction of Emotion From Spectrograms: Approaches Based on CNN and LSTM

Extraction of Emotion From Spectrograms: Approaches Based on CNN and LSTM
View Sample PDF
Author(s): Cecile Simo Tala (University of Ngaoundéré, Cameroon)
Copyright: 2024
Pages: 31
Source title: Global Perspectives on the Applications of Computer Vision in Cybersecurity
Source Author(s)/Editor(s): Franklin Tchakounté (University of Ngaoundere, Cameroon)and Marcellin Atemkeng (Rhodes University, South Africa)
DOI: 10.4018/978-1-6684-8127-1.ch005

Purchase

View Extraction of Emotion From Spectrograms: Approaches Based on CNN and LSTM on the publisher's website for pricing and purchasing information.

Abstract

Speech is the main source of communication between humans and is an efficient way to exchange information around the world. Emotion recognition through speech is an active research field that plays a crucial role in applications. SER is used in several areas of life, more precisely in the security field for the detection of fraudulent conversations. A pre-processing step was done on audios in order to reduce the noise and to eliminate the silence in the set of audios. The authors applied two approaches of the deep learning namely the LSTM and CNN for this domain in order to decide of the approach which saw better with the problem. They transformed treated audios into spectrograms for the model of the CNN. Then they used the technique of the SVD on these images to extract the matrices of characteristics for the entries of the LSTM. The proposed models were trained on these data and then tested to predict emotions. They used two databases, RAVDESS and EMO-DB, for the evaluation of the approaches. The experimental results proved the effectiveness of the model.

Related Content

Fahim Anzum, Ashratuz Zavin Asha, Lily Dey, Artemy Gavrilov, Fariha Iffath, Abu Quwsar Ohi, Liam Pond, Md. Shopon, Marina L. Gavrilova. © 2024. 46 pages.
Naomi Dassi Tchomte, Franklin Tchakounte, Ismael Abbo. © 2024. 42 pages.
Wyclife Ong'eta. © 2024. 13 pages.
Gabbi Evrard Tchoukouegno De Mofo, Ali Joan Beri Wacka, Franklin Tchakounte, Jean Marie Kuate Fotso. © 2024. 22 pages.
Cecile Simo Tala. © 2024. 31 pages.
Ismael Abbo, Naomi Dassi Tchomte. © 2024. 20 pages.
Stones Dalitso Chindipha. © 2024. 22 pages.
Body Bottom