Research trends in content processing of music audio signals: Difference between revisions

From HLT@INESC-ID

No edit summary
 
No edit summary
 
Line 1: Line 1:
__NOTOC__
__NOTOC__
{| width="45%" bgcolor="#f6faff" align="right" style="padding: 8px; border-style: solid; border-color: #aaaaaa; border-width: 1px;"
{{speaker|name=Fabien Gouyon
|&nbsp;[[Image:FabienGouyon.jpg|right|200px]]<br/>Researcher in the Telecommunications and Multimedia Unit of the INESC Porto (Institute for Systems and Computer Engineering of Porto, Portugal)  
|image=FabienGouyon.jpg
|}
|email=fgouyon@inescporto.pt
|www=http://www.inescporto.pt/~fgouyon
|bio=Researcher in the Telecommunications and Multimedia Unit of the INESC Porto (Institute for Systems and Computer Engineering of Porto, Portugal)  
}}
== Date ==
== Date ==



Latest revision as of 16:55, 19 June 2007

Fabien Gouyon
Fabien Gouyon
Fabien Gouyon

Researcher in the Telecommunications and Multimedia Unit of the INESC Porto (Institute for Systems and Computer Engineering of Porto, Portugal)

Addresses: www mail

Date

  • 15:00, Friday, June 29, 2007
  • 3rd floor meeting room

Speaker

Abstract

The standardization of world-wide low-latency networks, the extensive use of efficient search engines in everyday life, the continuously growing amount of multimedia information on the web, in broadcast data streams or in personal and professional databases and the rapid development of on-line music stores are revolutionizing our ways to interact with music (i.e. learning, making, buying, listening, exchanging, etc.). This opens the way to a number of exciting research problems, as those tackled in the field of Music Information Retrieval.

This is a relatively young and active research area focusing on the one hand on the automated description of musical material (audio, score, etc.) in terms of semantically meaningful tags, and on the other hand on the design of computer systems that permit pragmatic and meaningful exploitations of music content.

In this talk, I will provide an overview of state-of-the-art algorithms for the automatic description of music audio signals, both from a low-level perspective (focusing on signal characteristics) and a more musical perspective (focusing on musically-meaningful dimensions).

I will also provide examples of applications based on these descriptions, such as music identification, music browsing in large databases and music signal transformations.