E-raamat: Real-time Speech and Music Classification by Large Audio Feature Space Extraction

This book reports on an outstanding thesis thathas significantly advanced the state-of-the-art in the automated analysis andclassification of speech and music. Itdefines several standard acoustic parameter sets and describes theirimplementation in a novel, open-source, audio analysis framework calledopenSMILE, which has been accepted and intensively used worldwide. The bookoffers extensive descriptions of key methods for the automatic classificationof speech and music signals in real-life conditions and reports on theevaluation of the framework developed and the acoustic parameter sets that wereselected. It is not only intended as a manual for openSMILE users, but also andprimarily as a guide and source of inspiration for students and scientists involvedin the design of speech and music analysis methods that can robustly handlereal-life conditions.

Abstract.- Introduction.- Acoustic Features and Modelling.- Standard Baseline Feature Sets.- Real-time Incremental Processing.- Real-life Robustness.- Evaluation.- Discussion and Outlook.- Appendix.- Mel-frequency Filterbank Parameters.