benchmark systems for MIR (#ARIJIT BISWAS# )


Subject: benchmark systems for MIR
From:    #ARIJIT BISWAS#  <arijit17@xxxxxxxx>
Date:    Fri, 17 Oct 2008 16:18:32 +0800
List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>

This is a multi-part message in MIME format. ------_=_NextPart_001_01C93030.F14768C8 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-NAIMIME-Disclaimer: 1 X-NAIMIME-Modified: 1 Hello all! A novice question ;-) After designing one=C2=92s music information retrieval system how do one = measure the performance of one=C2=92s system? Do you compare the performance with some existing benchmark systems? If y= es, how could I get access to those benchmark systems? For example, if I=C2=92ve designed an audio fingerprinting system, with w= hom should I compare? Similarly, with whom should I compare my genre clas= sification or mood extraction algorithm? It would be really great if I could get such a list ;-) Best Regards, ~Arijit **Disclaimer**=0AThe sender of this email is NOT authorized to represent = or act on behalf of Nanyang Technological=0AUniversity in any matter or t= ransaction by means of using this email account.=0A=0ANanyang Technologic= al University will not be responsible for any content or views expressed = in this =0Aemail and this email does not express the views or opinions of= the Nanyang Technological University.=0A ------_=_NextPart_001_01C93030.F14768C8 Content-Type: text/HTML; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable X-NAIMIME-Disclaimer: 1 X-NAIMIME-Modified: 1 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN"> <HTML> <HEAD> <META HTTP-EQUIV=3D"Content-Type" CONTENT=3D"text/html; charset=3Diso-885= 9-1"> <META NAME=3D"Generator" CONTENT=3D"MS Exchange Server version 6.5.7652.2= 4"> <TITLE>benchmark systems for MIR</TITLE> </HEAD> <BODY> <!-- Converted from text/plain format --> <P><FONT SIZE=3D2>Hello all!<BR> <BR> A novice question ;-)<BR> <BR> After designing one&#146;s music information retrieval system how do one = measure the performance of one&#146;s system?<BR> Do you compare the performance with some existing benchmark systems? If y= es, how could I get access to those benchmark systems?<BR> <BR> For example, if I&#146;ve designed an audio fingerprinting system, with w= hom should I compare? Similarly, with whom should I compare my genre clas= sification or mood extraction algorithm?<BR> <BR> It would be really great if I could get such a list ;-)<BR> <BR> Best Regards,<BR> ~Arijit<BR> </FONT> </P> <DIV><P><HR> **Disclaimer**<BR>=0AThe sender of this email is NOT authorized to repres= ent or act on behalf of Nanyang Technological<BR>=0AUniversity in any mat= ter or transaction by means of using this email account.<BR>=0A<BR>=0ANan= yang Technological University will not be responsible for any content or = views expressed in this <BR>=0Aemail and this email does not express the = views or opinions of the Nanyang Technological University.<BR>=0A </P></DIV> </BODY> </HTML> ------_=_NextPart_001_01C93030.F14768C8--


This message came from the mail archive
http://www.auditory.org/postings/2008/
maintained by:
DAn Ellis <dpwe@ee.columbia.edu>
Electrical Engineering Dept., Columbia University