Notícies Notícies

Torna a la pàgina principal
Vés enrere

Thesis defence: Dr. Sergio Oramas

Thesis defence: Dr. Sergio Oramas


Knowledge Extraction and Representation Learning for Music Recommendation and Classification

-Dr. Sergio Oramas

Thesis supervisor: Dr. Xavier Serra


Brief description:
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.
Experience as PhD student:
I really enjoyed my 4 years as a PhD student at DTIC. The best asset is the people, the students, the faculty members, and the administrative staff. This is the best University I have been during my academic life. I'm very grateful to have done my PhD here. Specially I like the Music Technology Group, where I was involved. I got a lot of support and could travel to many conferences where I learnt a lot of things, and I was also surrounded by very brilliant people from whom I learnt many things. I have a special remember to the "pizza workshop" we had at the beginning of my PhD with all new PhD students from DTIC. This workshop made me know great researchers from the TALN group with whom I collaborated during all these years publishing many papers together. It's a pity this workshop had been discontinued, this department is full of brilliant people, and it's very nice and useful to know each other. All in all, doing this PhD has been a wonderful experience.