Focal Loss Based Residual Convolutional Neural Network For Speech Emotion Recognition

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytripathi2019focal

Related papers

• Attention Based Fully Convolutional Network For Speech Emotion Recognition (2018)15.25
• Learning Discriminative Features Using Center Loss And Reconstruction As Regularizer For Speech Emotion Recognition (2019)0.00
• Light-sernet: A Lightweight Fully Convolutional Neural Network For Speech Emotion Recognition (2021)14.90
• Deep Residual Local Feature Learning For Speech Emotion Recognition (2020)7.16
• Emotion Recognition From Speech With Recurrent Neural Networks (2017)0.00
• Deep Learning Based Emotion Recognition System Using Speech Features And Transcriptions (2019)0.00
• Emotion Recognition System From Speech And Visual Information Based On Convolutional Neural Networks (2020)10.21
• Evaluating Gammatone Frequency Cepstral Coefficients With Neural Networks For Emotion Recognition From Speech (2018)0.00