Thesis Open Access

Knowledge Extraction and Representation Learning for Music Recommendation and Classification

Oramas, Sergio

Thesis supervisor(s)

Serra, Xavier

In this thesis, we address the problems of classifying and recommending music present in large collections. We focus on the semantic enrichment of descriptions associated to musical items (e.g., artists biographies, album reviews, metadata), and the exploitation of multimodal data (e.g., text, audio, images). To this end, we first focus on the problem of linking music-related texts with online knowledge repositories and on the automated construction of music knowledge bases. Then, we show how modeling semantic information may impact musicological studies and helps to outperform purely text-based approaches in music similarity, classification, and recommendation. Next, we focus on learning new data representations from multimodal content using deep learning architectures, addressing the problems of cold-start music recommendation and multi-label music genre classification, combining audio, text, and images. We show how the semantic enrichment of texts and the combination of learned data representations improve the performance on both tasks. 

Full list of associated resources Slides Presentation video:
Files (6.4 MB)
Name Size
6.4 MB Download
All versions This version
Views 238169
Downloads 8055
Data volume 510.7 MB351.7 MB
Unique views 233164
Unique downloads 6744


Cite as