Technical Program

Paper Detail

Paper:	SLP-P3.6
Session:	Novel LVCSR Algorithms
Time:	Tuesday, May 16, 14:00 - 16:00
Presentation:	Poster
Topic:	Speech and Spoken Language Processing: Emotion Recognition in General ASR
Title:	Stress Level Classification of Speech Using Euclidean Distance Metrics in a Novel Hybrid Multi-Dimensional Feature Space
Authors:	Evan Ruzanski, John H. L. Hansen, University of Colorado at Boulder, United States; James Meyerhoff, George Saviolakis, Walter Reed Army Institute of Research, United States; William Norris, Terry Wollert, Federal Law Enforcement Training Center, United States
Abstract:	Presently, automatic stress detection methods for speech employ a binary decision approach, deciding whether the speaker is or is not under stress. Since the amount of stress a speaker is under varies and can change gradually, a reliable stress level detection scheme becomes necessary to accurately assess the condition of the speaker. Such a capability is pertinent to a number of applications, such as for those personnel in law enforcement positions. Using speech and biometric data collected from a real-world, variable-stress level law enforcement training scenario, this study illustrates two methods for automatically assessing stress levels in speech using a hybrid multi-dimensional feature space comprised of frequency-based and Teager Energy Operator-based features. The first approach uses a nearest neighbor-type clustering scheme at the vowel token level to classify speech data into one of three levels of stress, yielding an overall error rate of 50.5%. The second approach employs accumulated Euclidean distance metric weighting at the sentence-level to yield a relative improvement of 12.1% in performance.