EmoHRNet: High-Resolution Neural Network Based Speech Emotion Recognition

2025/10/07 by Muppidi, Akshay, Radfar, Martin
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Sound (cs.SD)

paper · doi:10.48550/arxiv.2510.06072

Abstract

Speech emotion recognition (SER) is pivotal for enhancing human-machine interactions. This paper introduces "EmoHRNet", a novel adaptation of High-Resolution Networks (HRNet) tailored for SER. The HRNet structure is designed to maintain high-resolution representations from the initial to the final layers. By transforming audio samples into spectrograms, EmoHRNet leverages the HRNet architecture to extract high-level features. EmoHRNet's unique architecture maintains high-resolution representations throughout, capturing both granular and overarching emotional cues from speech signals. The model outperforms leading models, achieving accuracies of 92.45% on RAVDESS, 80.06% on IEMOCAP, and 92.77% on EMOVO. Thus, we show that EmoHRNet sets a new benchmark in the SER domain.

Citations

• CTL-MTNet: A Novel CapsNet and Transfer Learning-Based Mixed Task Net for the Single-Corpus and Cross-Corpus Speech Emotion Recognition
• Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition
• Speech Emotion Recognition Using Quaternion Convolutional Neural\n Networks
• Deep High-Resolution Representation Learning for Visual Recognition
• Deep High-Resolution Representation Learning for Visual Recognition
• Deep High-Resolution Representation Learning for Human Pose Estimation

Related

• EmoAugNet: A Signal-Augmented Hybrid CNN-LSTM Framework for Speech Emotion Recognition
• DeepEmoNet: Building Machine Learning Models for Automatic Emotion Recognition in Human Speeches
• Amplifying Emotional Signals: Data-Efficient Deep Learning for Robust Speech Emotion Recognition
• EmoFormer: A Text-Independent Speech Emotion Recognition using a Hybrid Transformer-CNN model
• Toward Efficient Speech Emotion Recognition via Spectral Learning and Attention