This app consists of a series of Matlab routines useful for various aspects of prosodic analysis of speech, in particular F0 and harmonic analysis, loudness analysis, and voice-source analysis. Much of this software was written to support the research outlined in "A Computational Model for the Automatic Recognition of Affect in Speech". CREDIT of the original copy to Raul Fernandez. It is free software; you can redistribute it and/or modify it under the terms of the MIT General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. To access all the routines, you may want to run the setUpPaths.m file included in this distribution, or modify your MATLAB setup to run it at start-up time. The Contents.m file includes a high-level description of the routines included in this package. For more specific information on how to use a particular routine, type HELP and the routine name under the MATLAB environment. There are 3 main directories in this distribution ./Voice_Source ./F0_HarmonicAnalysis ./Loudness which include various subroutines for the analysis of voice source, harmonic analysis, and loudness respectively. In addition, the ./Utils subdirectory contains various utilities that you may find useful outside of the above applications. I have also released various MATLAB routines not authored by me. These are included in ./Utils/DIN_2045631_V201.4.20 ./Utils/Voicebox The software included there has been made publically and freely available before, and has been used here to support the work which I have authored. I am redistributing it further to facilitate running my code. Note that there is at least one routine in this package which invokes a licensed MATLAB function (e.g., from the Optimization Toolbox), which I'm unable to release. So you may need to have access to the appropriate toolboxes to run some of the code above. If you find the code here useful, and you publish any results obtained with the help of it, consider crediting it with one of the following references in your paper: - R. Fernandez, "A Computational Model for the Automatic Recognition of Affect in Speech," Ph.D. dissertation, (http://affect.media.mit.edu/pdfs/04.fernandez-phd.pdf), Media Arts and Sciences, Massachusetts Institute of Technology, 2004. - R. Fernandez and R. W. Picard, "Classical and Novel Discriminant Features for Affect Recognition from Speech," Proc. Interspeech 2005, pp. 473-476, Lisbon, Portugal, 2005.