Emotion recognition of audio/speech data using deep learning approaches. Issue 6 (17th August 2020)

• Record Type: Journal Article
• Authors: Gupta, Vedika; Juyal, Stuti; Singh, Gurvinder Pal; Killa, Chirag; Gupta, Nishant
• Is Part Of: Journal of information & optimization sciences. Volume 41:Issue 6(2020)
• Page Start: 1309
• Page End: 1317
• Publication Date: 2020-08-17
• Subjects: 68T10; Convolutional neural network -- Deep learning -- Emotion recognition -- Recurrent neural network -- Speech; Electronic data processing -- Periodicals; Information science -- Periodicals; Mathematical optimization -- Periodicals; 519.6
• DOI: 10.1080/02522667.2020.1809089
• Languages: English
• ISSNs: 0252-2667

Abstract

Abstract: Speech has been the most prominent and intelligent mode of sound. It is an effective medium to communicate the emotions and attitude in a particular language. Researchers have been extensively using speech to understand the emotions of a person. Contemplating emotions by intonation and pitch of voice and relative loudness can be used for enhancing human computer interaction. In this work, we have surveyed feature extraction techniques based on prosodic features or spectral feature extraction such as MFCC, LPCC, LPC, etc. and found out that MFCC extracts the best features for recognition of emotional content. This research work utilizes some of the best existing classification techniques for recognizing human emotions and conducts a detailed comparative analysis based on statistical and mathematical results. Finally, this paper proposes an optimal model DSCNN for raw spectrogram that resulted in an un-weighted accuracy of 61% for raw spectrogram (with noise) and 79% for clean spectrogram (without noise) for the enhancement of the human emotion evaluation system.