robert@aerospace.aero.org (Bob Statsinger) (03/15/90)
In article <12355@venera.isi.edu> smoliar@vaxa.isi.edu.UUCP (Stephen Smoliar) writes: > >Readers more interested in what can be done with neural networks may wish to >check out Peter Todd's contribution to the 1988 Connectionist Models Summer >School. Todd is a psychologist, and he seems more concerned with modeling >phenomena which have been observed in psychological experiments. I would >say there is still some doubt as to how relevant those experiments are to >music as it is actually practiced, but at least Todd appears to be approaching >the problem more scientifically. The two most recent issues (vols 12 and 13) of "Computer Music Journal" are completely devoted to neural nets and connectionism as applied to musical composition and models of music perception. Todd has a GREAT article in vol 13 on a recurrent network he developed for algorithmic composition. There are also backpropagation models of pitch perception (Jenkins), bidirectional linear nets for inferring tonality (Bharucha), and in vol 12 an ART system for musical classification. This semester I am working on applying invariant object recognition to attempt to model the recognition of musical melody independent of key signature (invariance with respect to tempo and mild distortion invariance are also desirable). I have not seen this attempted anywhere in the literature that I've seen so far. If anyone has seen such an attempt, PLEASE respond in a followup posting and/or by e-mail. Thanx much. -- Bob Statsinger Robert@aerospace.aero.org The employers expressed herein are strictly mine and are not necessarily those of my opinion's....uh..er...whatever...
smoliar@vaxa.isi.edu (Stephen Smoliar) (03/16/90)
In article <68750@aerospace.AERO.ORG> robert@aero.UUCP (Bob Statsinger) writes: > > The two most recent issues (vols 12 and 13) of "Computer Music >Journal" are completely devoted to neural nets and connectionism as >applied to musical composition and models of music perception. Todd has a >GREAT article in vol 13 on a recurrent network he developed for >algorithmic composition. There are also backpropagation models of >pitch perception (Jenkins), bidirectional linear nets for >inferring tonality (Bharucha), and in vol 12 an ART system >for musical classification. > Thanks for coming to my rescue, Bob! I received two electronic mail requests for details but was tardy in responding due to being snowed under by two papers I'm trying to wrap up! Nevertheless, your citation had better get corrected before things get out of hand. The two issues are Numbers 3 and 4 of Volume 13 (not volumes 12 and 13). For those interested in the specific articles, the Jenkins piece on pitch perception and Gjerdingen's ART piece are in Number 3. Bharucha and Todd are in Number 4. Personally, I did not think very much about the ART article; but I am prepared to be persuaded otherwise. ========================================================================= USPS: Stephen Smoliar USC Information Sciences Institute 4676 Admiralty Way Suite 1001 Marina del Rey, California 90292-6695 Internet: smoliar@vaxa.isi.edu "Only a schoolteacher innocent of how literature is made could have written such a line."--Gore Vidal