Digital Music Emotion Recognition Technique Using Multi-Class Support Vector Machine

Abstract

This research presents a recognition method for digital music emotion, specifically focusing on addressing the challenge of recognizing sampling-based digital music formats. The proposed method combines sound feature parameters and music theory feature parameters and employs a multi-class support vector machine (SVM) based sorting technology. The method involves four key steps: preprocessing, feature extraction, training the multi-class SVM, and recognition. Emotions such as happiness, impassion, sadness, and relaxation are classified within a sampling-based digital music format file. In addition to extracting common sound features used in speech recognition, a range of music theory features are also extracted. The adoption of the SVM-based sorting method results in rapid learning speed, high sorting precision ratio, and improved recognition efficiency.