Can I read A Multimodal Hierarchical Approach To Speech Emotion Recognition on EtoBox?

A Multimodal Hierarchical Approach To Speech Emotion Recognition by somilcodes is a document available to read on EtoBox.

What is A Multimodal Hierarchical Approach To Speech Emotion Recognition about?

This document presents a deep learning-based hierarchical approach for speech emotion recognition (SER) that utilizes both audio and text modalities. The proposed system achieves SER accuracies of 81.2%, 81.7%, and 74.5% on three different datasets, demonstrating superior performance compared to existing techniques. Key contributions include the integration of various audio features and the use of ELMo v2 for extracting textual features, enhancing the recognition of emotions in speech.

Author

somilcodes

Language

EN