Start ReadSpeaker XT

Contact




Seminar at Speech, Music and Hearing:

Mining User-generated Data for Music Information Retrieval

Markus Schedl, Johannes Kepler University, Austria

Abstract

Social media represents an unprecedented source for information about every topic of our daily lives. As music plays a vital role for many people, information about music items and artists is found in large amounts in user-generated data. Although the two research fields of \"Music Information Retrieval\" (MIR) and \"Social Media Mining\" (SMM) seem only marginally overlapping, they have in common that both have recently attracted a lot of attention, both in society and in the research community. I will first briefly introduce important concepts and tasks in MIR. Subsequently, I will present examples of how SMM research can be beneficially applied to solve some of the challenges currently faced in MIR research. More precisely, our work from which selected topics will be presented, includes: * listening pattern extraction and analysis * geospatial music taste analysis (\"mainstreaminess\" of populations) * context-based music similarity estimates from social media * visualizing music listening behavior * music popularity estimation in social media

15:15 - 17:00
Wednesday March 20, 2013

The seminar is held in Seminarierummet.

| Show complete seminar list







Published by: TMH, Speech, Music and Hearing
Webmaster, webmaster@speech.kth.se

Last updated: Wednesday, 23-Jun-2010 09:22:46 MEST