| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 1.87 MB | Adobe PDF |
Advisor(s)
Abstract(s)
We present a prototype software for multi-user music library management using the perceived emotional content of songs. The tool offers music playback features, song filtering by metadata, and automatic emotion prediction based on arousal and valence, with the possibility of personalizing the predictions by allowing each user to edit these values based on their own emotion assessment. This is an important feature for handling both classification errors and subjectivity issues, which are inherent aspects of emotion perception. A path-based playlist generation function is also implemented. A multi-modal audio-lyrics regression methodology is proposed for emotion prediction, with accompanying validation experiments on the MERGE dataset. The results obtained are promising, showing higher overall performance on train-validate-test splits (73.20% F1-score with the best dataset/split combination).
Description
Keywords
Music Emotion Recognition Machine Learning Deep Learning Software Music Information Retrieval
Citation
Publisher
SCITEPRESS - Science and Technology Publications