Work

Focal Loss based Residual Convolutional Neural Network for Speech Emotion Recognition

Year: 2019

Type: preprint

Abstract: This paper proposes a Residual Convolutional Neural Network (ResNet) based on speech features and trained under Focal Loss to recognize emotion in speech. Speech features such as Spectrogram and Mel-frequency Cepstral Coefficients (MFCCs) have shown the ability to characterize emotion better than just plain text. Further Focal Loss, first used in One-Stage Object Detectors, has shown the ability to focus the training process more towards hard-examples and down-weight the loss assigned to well-classified examples, thus preventing the model from being overwhelmed by easily classifiable examples.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1906.05682

Authors: Tripathi, Suraj, Kumar, Abhay, Ramesh, Abhiram, Singh, Chirag, Yenigalla, Promod

Institutions: Samsung (South Korea), Samsung (India)

Language: English

Topic: Emotion and Mood Recognition

Subfield: Experimental and Cognitive Psychology

Field: Psychology

Domain: Social Sciences

Open Access status: green

OpenAlex ID: W2951589696

Cites: 22

Cited by: 13

Related to: 20