The Random Subspace Method for Constructing Decision Forests
IEEE Transactions on Pattern Analysis and Machine Intelligence
Vocal communication of emotion: a review of research paradigms
Speech Communication - Special issue on speech and emotion
The WEKA data mining software: an update
ACM SIGKDD Explorations Newsletter
EmotionSense: a mobile phones based adaptive platform for experimental social psychology research
Proceedings of the 12th ACM international conference on Ubiquitous computing
Opensmile: the munich versatile and fast open-source audio feature extractor
Proceedings of the international conference on Multimedia
IEEE Transactions on Audio, Speech, and Language Processing
Hi-index | 0.00 |
Emotional stress is commonly experienced while speaking in public, producing changes to the various speech productions subsystems, affecting the speech signal in predictable ways and being easily conveyed to listeners. Speech stress indicators, however, are typically studied under laboratory settings, allowing little generalization to real life settings. To bridge this gap, we propose an interdisciplinary approach to assess speech stress during public speaking events, based on a platform that records speech simultaneously annotated with physiological and psychological measures. This approach enables the collection of a large corpus of annotated speech in ecological settings, i.e. in objectively stressing situations. We also propose and implement a methodology to assess listeners evaluation of stress including psychologists, and overall public. The platform has been in use for the past 5 months, and we have collected 13 complete samples after the initial iterative development procedure. Preliminary results indicate that the proposed user-friendly platform is an accurate and robust method to collect annotated speech under ecological settings that can be processed to obtain speech stress indicators. The findings will be used primarily in the design of computer and mobile assisted voice coaching applications, but the outreach extends to mobile emotion sensing for individuals and crowds.