Collect and setup additional speech datasets

[yoshua]

Get other relevant datasets which could help training an emotion classifier from speech, including music+mood data, unlabeled speech with emotional content, and most importantly, emotion+speech data such as in http://emotion-research.net/databases and maybe more. Guillaume A will investigate the Vera Am Mittag data and Humaine data. We might get also data from the 'emotion challenge' at Interspeech 2009.

Define which parts of the datasets will be used for training and which parts for validation (coordinate with +Razvan).