Re: MIDI file analysis (alexander lerch )


Subject: Re: MIDI file analysis
From:    alexander lerch  <lerch@xxxxxxxx>
Date:    Thu, 1 Feb 2007 10:18:27 +0100
List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>

Hi, Michael Fulton wrote: > 1. Algorithms to "transcribe" MIDI files into some form which conveys > either : melody lines, key signatures, tempo, time sigs, and chord > progressions etc Although in my opinion these are a too complex topics to be referred to simply as transcription, I think the Matlab Miditoolbox (http://www.jyu.fi/musica/miditoolbox/) might be a first starting point. > 2. Some "metrics" currently beiing employed to measure musical similarity . There have been publications dealing with musical similarity in the proceedings of ISMIR and MIREX (http://www.ismir.net/) Naturally, all these metrics will depend on the definition of musical similarity, and on the ability to (automatically) extract the required information from MIDI or audio. Cheers, Alexander -- dipl. ing. alexander lerch zplane.development :www.zplane.de katzbachstr.21 d-10965 berlin fon: +49.30.854 09 15.0 fax: +49.30.854 09 15.5


This message came from the mail archive
http://www.auditory.org/postings/2007/
maintained by:
DAn Ellis <dpwe@ee.columbia.edu>
Electrical Engineering Dept., Columbia University