Being a western dilettante dabbler in world musics, I wonder what people with significantly different experiences hear in their own, and western european musics. One way of finding this out has been in listening to western versions of non-western musics (Colin McPhee for example), or non-western musicians writing in the european (tonal) tradition. There is now a small number of CDs on Naxos of Japanese composers from the last century writing in 'western' (tonal) idioms.
For me, as a composer, what is interesting is how differently many of them understand / reflect upon the 'limits' of tonality. Frequently, the harmony is either (bland) textbook, or oriented in other directions. It has an accent of dialect of (an)other (set of) cultural cues. The "identity" (and therefore [emotional] response) will be based upon the detection and "well-formed" of these cues. As one person said of a piece I wrote, "It is a western woman wearing qi-pao (traditional chinese dress)."
Based on my western background I also noted that some of the "emotions" listed, I would call moods. And there may be a difference between what is done, and the intended projected meaning. For example, in theater, to project boredom, one doesn't bore the audience: http://en.wikipedia.org/wiki/Waiting_for_Godot , a play that has been described as "A play in which nothing happens, twice." Memory and affect are also highlighted by characters such Peeperkorn in Magic Mountain, where the effect of personality mitigates the need for explicit content.
I noted in slide 5 of the documentation that the word / emotion / mood / sentiment -- one of my favorites, was missing; humor. Or maybe there is no humorous music, only responses which detect humor. ... Did you hear the joke one computer told another computer?
Best Kevin
Date: Sat, 28 Feb 2009 10:34:42 +0800 From: affige yang <affige@xxxxxxxxx>Subject: Re: Music, emotion, memory of passages and content analysis (LSA)Hi, Daniel:I am a phd student of EECS. I don't know if it is relevant, but I have some preliminary results related to the automatic prediction of emotion values of music.http://mpac.ee.ntu.edu.tw/~yihsuan/publication.htmlY.-H. Yang et al, "A regression approach to music emotion recognition," IEEE Transactions on Audio, Speech and Language Processing (TASLP), vol. 16, no. 2, pp. 448-457, Feb. 2008.In this paper, we formulate music emotion recognition as a regression problem and predict the arousal and valence values (numerical values) of music. The ground truth data needed for training an automatic regression model is obtained through a subjective test. Subjects are asked to rate the arousal and valence values of a number of songs. Features are extracted from the audio signal to represent the songs, and support vector regression (SVR) is adopted to train the regression model.Y.-H. Yang and H.-H. Chen, "Music emotion ranking," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing 2009 (ICASSP'09), Taipei, Taiwan, accepted. The cognitive load of rating emotion may be too high. In this paper, we propose a ranking measure and ask subject to annotate emotion in a comparative way.Sincerely yours, -- Yi-Hsuan Yang (Eric), Ph.D. candidate, MPAC Lab, Graduate Institute of Communication Engineering, National Taiwan University. http://mpac.ee.ntu.edu.tw/~yihsuan/