Sensors 2009, 9(12), 9858-9872; doi:10.3390/s91209858

Application of Poincare-Mapping of Voiced-Speech Segments for Emotion Sensing

1 Institute of Electronics, Technical University of Lodz, Poland, Wolczanska 213/215, 90-924 Lodz, Poland 2 Division of Electrical, Electronics and Computer Engineering, Chonbuk National University, 561-756 Chonju, Korea
* Author to whom correspondence should be addressed.
Received: 30 October 2009; in revised form: 14 November 2009 / Accepted: 17 November 2009 / Published: 3 December 2009
(This article belongs to the Section Physical Sensors)
PDF Full-text Download PDF Full-Text [372 KB, uploaded 4 December 2009 09:53 CET]
Abstract: The following paper introduces a group of novel speech-signal descriptors that reflect phoneme-pronunciation variability and that can be considered as potentially useful features for emotion sensing. The proposed group includes a set of statistical parameters of Poincare maps, derived for formant-frequency evolution and energy evolution of voiced-speech segments. Two groups of Poincare-map characteristics were considered in the research: descriptors of sample-scatter, which reflect magnitudes of phone-uttering variations and descriptors of cross-correlations that exist among samples and that evaluate consistency of variations. It has been shown that inclusion of the proposed characteristics into the pool of commonly used speech descriptors, results in a noticeable increase—at the level of 10%—in emotion sensing performance. Standard pattern recognition methodology has been adopted for evaluation of the proposed descriptors, with the assumption that three- or four-dimensional feature spaces can provide sufficient emotion sensing. Binary decision trees have been selected for data classification, as they provide with detailed information on emotion-specific discriminative power of various speech descriptors.
Keywords: emotion sensing; feature selection; Poincare-maps; decision-trees

Article Statistics

Load and display the download statistics.

Citations to this Article

Cite This Article

MDPI and ACS Style

Ślot, K.; Bronakowski, Ł.; Cichosz, J.; Kim, H. Application of Poincare-Mapping of Voiced-Speech Segments for Emotion Sensing. Sensors 2009, 9, 9858-9872.

AMA Style

Ślot K, Bronakowski Ł, Cichosz J, Kim H. Application of Poincare-Mapping of Voiced-Speech Segments for Emotion Sensing. Sensors. 2009; 9(12):9858-9872.

Chicago/Turabian Style

Ślot, Krzysztof; Bronakowski, Łukasz; Cichosz, Jaroslaw; Kim, Hyongsuk. 2009. "Application of Poincare-Mapping of Voiced-Speech Segments for Emotion Sensing." Sensors 9, no. 12: 9858-9872.

Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert