Finding the Most Uniform Changes in Vowel Polygon Caused by Psychological Stress

Using vowel polygons, exactly their parameters, is chosen as the criterion for achievement of differences between normal state of speaker and relevant speech under real psychological stress. All results were experimentally obtained by created software for vowel polygon analysis applied on ExamStress database. Selected 6 methods based on cross-correlation of different features were classified by the coefficient of variation and for each individual vowel polygon, the efficiency coefficient marking the most significant and uniform differences between stressed and normal speech were calculated. Using the mean of cross- correlation values received for area difference with vector length and angle can be classified as the best method for observing generated differences. Generally, best results for stress detection are achieved by vowel triangles created by /i/-/o/-/u/ and /a/-/i/-/o/ vowel triangles in formant planes containing the fifth formant F5 combined with other formants.

[1]  John H. L. Hansen,et al.  Getting started with SUSAS: a speech under simulated and actual stress database , 1997, EUROSPEECH.

[2]  Everyday stressors and gender differences in daily distress. , 1998 .

[3]  Hynek Hermansky,et al.  Segmentation of speech for speaker and language recognition , 2003, INTERSPEECH.

[4]  Gregory S. Kolt,et al.  Eustress, distress, and interpretation in occupational stress , 2003 .

[5]  Guy J. Brown,et al.  Speech and crosstalk detection in multichannel audio , 2005, IEEE Transactions on Speech and Audio Processing.

[6]  M. Sigmund,et al.  Introducing the Database ExamStress for Speech under Stress , 2006, Proceedings of the 7th Nordic Signal Processing Symposium - NORSIG 2006.

[7]  V. Dellwo.  Rhythm and Speech Rate: A Variation Coefficient for deltaC , 2006 .

[8]  Linda Polka,et al.  Developmental and cross-linguistic variation in the infant vowel space: the case of Canadian English and Canadian French. , 2006, The Journal of the Acoustical Society of America.

[9]  Amitava Chatterjee,et al.  Support vector machines employing cross-correlation for emotional speech recognition , 2009 .

[10]  Nicholas B. Allen,et al.  Stress Detection Using Speech Spectrograms and Sigma-pi Neuron Units , 2009, 2009 Fifth International Conference on Natural Computation.

[11]  C. Pelachaud,et al.  Emotion-Oriented Systems: The Humaine Handbook , 2011 .

[12]  Milan Sigmund,et al.  Influence of Psychological Stress on Formant Structure of Vowels , 2012 .

[13]  I. Mcloughlin,et al.  A comprehensive vowel space for whispered speech. , 2012, Journal of voice : official journal of the Voice Foundation.

[14]  Kazuya Takeda,et al.  Physical characteristics of vocal folds during speech under stress , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  M. Hariharan,et al.  Assimilate the auditory scale with wavelet packet filters for multistyle classification of speech under stress , 2012, 2012 International Conference on Biomedical Engineering (ICoBE).

[16]  M. Hariharan,et al.  Human Affective (Emotion) behaviour analysis using speech signals: A review , 2012, 2012 International Conference on Biomedical Engineering (ICoBE).

[17]  Anna Esposito,et al.  Classification of emotional speech units in call centre interactions , 2013, 2013 IEEE 4th International Conference on Cognitive Infocommunications (CogInfoCom).

[18]  Ladislav Polak,et al.  Algorithms for vowel recognition in fluent speech based on formant positions , 2013, 2013 36th International Conference on Telecommunications and Signal Processing (TSP).

[19]  A. Pribilová,et al.  Determination of Formant Features in Czech and Slovak for GMM Emotional Speech Classifier Ji ř , 2013 .

[20]  M. Sigmund,et al.  Speaker dependent changes in formants based on normalization of vowel triangle , 2013, 2013 23rd International Conference Radioelektronika (RADIOELEKTRONIKA).

[21]  Jennifer byrd-craven,et al.  Vocal indices of stress: a review. , 2013, Journal of voice : official journal of the Voice Foundation.

[22]  Mykola Pechenizkiy,et al.  Stress detection from speech and Galvanic Skin Response signals , 2013, Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems.

[23]  Milan Sigmund.  Statistical Analysis of Fundamental Frequency Based Features in Speech under Stress , 2013, Inf. Technol. Control..

[24]  M. Lech,et al.  Stress and emotion recognition using acoustic speech analysis , 2014 .

[25]  Miroslav Stanek,et al.  Comparison of speaker individuality in triangle areas of plane formant spaces , 2014, 2014 24th International Conference Radioelektronika.

[26]  R. Masters,et al.  Analogy instruction and speech performance under psychological stress. , 2014, Journal of voice : official journal of the Voice Foundation.

[27]  S. W. Gregory,et al.  Stress Reactivity of Emotional and Verbal Speech Content in Schizophrenia , 2014, The Journal of nervous and mental disease.

[28]  Darko Brodić,et al.  The Effects of the Active Hypoxia to the Speech Signal Inharmonicity , 2014 .

[29]  Jason A. Whitfield,et al.  Articulatory-acoustic vowel space: application to clear speech in individuals with Parkinson's disease. , 2014, Journal of communication disorders.

[30]  Maria Dietrich,et al.  Psychobiological stress reactivity and personality in persons with high and low stressor-induced extralaryngeal reactivity. , 2014, Journal of speech, language, and hearing research : JSLHR.

[31]  M. Duff,et al.  Acute stress reduces speech fluency , 2014, Biological Psychology.

[32]  Miroslav Stanek.  Software for generation and analysis of vowel polygons , 2015, 2015 38th International Conference on Telecommunications and Signal Processing (TSP).