If the problem that you are actually addresing is audio/speech signal segmentation and distinguishing between the speech and music, see this:  http://www.sersc.org/journals/IJSIP/vol5_no1/4.pdf I could be wrong on this, but, as per http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=4579953&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D4579953; Praat seems to be not so usefull for polyphonic music analysis, except if augmented with some additional pre-filtering for the purpose of segmentation.

If the problem that you are actually addresing is audio/speech signal segmentation and distinguishing between the speech and music, see: 

Theodorou T., Mporas I. and Fakotakis N., "Automatic Sound Classification of Radio Broadcast News", Int. J. Sig. Proc., Image Proc. Pattern Recognition, 5(1), 2012

I could be wrong on this but Praat seems to be not so usefull for polyphonic music analysis, except if augmented with some additional pre-filtering for the purpose of segmentation:

Makarand Ramesh, V.; Sahasrabuddhe, H.V.; , "Exploring Data Analysis in Music Using Tool Praat," Emerging Trends in Engineering and Technology, 2008. First International Conference on, pp.508-509