13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Classification of Stressed Speech Using Physical Parameters Derived from Two-Mass Model

Xiao Yao (1), Takatoshi Jitsuhiro (1,2), Chiyomi Miyajima (1), Norihide Kitaoka (1), Kazuya Takeda (1)

(1) Department of Media Science, Graduate School of Nagoya University, Nagoya, Japan
(2) Department of Media Informatics, Aichi University of Technology, Nagoya, Japan

In this study, we investigate physical parameters which can be used to classify speech as either stressed or neutral based on a two-mass vocal fold model. The model attempts to characterize the behavior of the vocal folds and fluid airflow properties when stress is present. The two-mass model is fitted to real speech to estimate the values of physical parameters that represent the stiffness of vocal folds, vocal fold viscosity loss, and subglottal pressure coming from the lungs. The estimated parameters can be used to distinguish stressed speech from neutral speech because these parameters can represent the mechanisms of vocal folds under stress. We propose combinations of physical parameters as features for classification. Experimental results show that our proposed features achieved better classification performance than features derived from traditional methods.

Index Terms: physical parameters, two-mass model, speech under stress, stress classification

Full Paper

Bibliographic reference.  Yao, Xiao / Jitsuhiro, Takatoshi / Miyajima, Chiyomi / Kitaoka, Norihide / Takeda, Kazuya (2012): "Classification of stressed speech using physical parameters derived from two-mass model", In INTERSPEECH-2012, 1223-1226.