‘Hands‐On’: Existing Toolkits and Practical Tutorial
Björn Wolfgang Schuller, Anton M. Batliner · 2013
This chapter provides practical examples of paralinguistic feature extraction and live emotion recognition with the openSMILE (open-source Speech and Music Interpretation by Largespace Extraction) toolkit. The toolkit has a strong focus on real-time, incremental processing. Moreover, openSMILE provides a simple console application where modular feature extraction components can be freely configured and connected via a single configuration file. Both incremental on-line processing for live applications and off-line batch processing are supported. The chapter gives an overview of related toolkits which can also be used to extract some features, or can be used together with openSMILE to perform machine learning tasks and model learning. Then it briefly introduces and describes the openSMILE toolkit and its architecture and finally present a brief hands-on ‘computational paralinguistics how-to’.