Music Information Retrieval

Trudie Sandrock will present the Department of Statistical Science seminar, with a talk entitled, "Music Information Retrieval"

Music information retrieval (MIR) is primarily concerned with the reduction of music to a workable data format and then extracting meaningful information from the data.  MIR has been a very active field of research in the past decade and it is an interdisciplinary research area, spanning fields such as Music, Mathematics, Statistics, Computer Science, Engineering and Psychology.  While Statistics is a field well-suited to dealing with the type of research problems encountered in MIR – and statistical techniques are often used in MIR research – researchers in the field are currently mostly from a computer science (machine learning) background. 

In this talk, Trudie will aim to give a very brief introduction to the field of MIR and briefly highlight some of the issues encountered in MIR research.  She will also touch on the statistical techniques underpinning well-known MIR apps such as Shazam and Soundhound.

 Trudie has worked in statistical environments in the financial services industry from 1999 to 2008 - locally at Old Mutual, Sanlam and Investec Private Bank and in the United Kingdom at Hargreaves Landsdown.  She is currently a postdoctoral research fellow at the University of Stellenbosch, and her research interests include multi-label classification  and music information retrieval.

BCom (Maths & Stats) – Nelson Mandela Metropolitan University, 1998

BCom (Hons) (Statistics) – University of South Africa, 2000

MCom (Mathematical Statistics) – University of Stellenbosch, 2003

PhD (Statistics) – University of Stellenbosch, 2013



Monday, February 22, 2016 - 13:00

Lecture Theatre 3, PD Hahn, Upper Campus, UCT