Emotional state and its impact on voice authentication accuracy

The paper deals with the increasing accuracy of voice authentication methods. The developed algorithm first extracts segmental parameters, such as Zero Crossing Rate, the Fundamental Frequency and Mel-frequency cepstral coefficients from voice. Based on these parameters, the neural network classifier detects the speaker's emotional state. These parameters shape the distribution of neurons in Kohonen maps, forming clusters of neurons on the map characterizing a particular emotional state. Using regression analysis, we can calculate the function of the parameters of individual emotional states. This relationship increases voice authentication accuracy and prevents unjust rejection.

[1]  Eberhard Fuchs,et al.  Modulation of binding sites for corticotropin-releasing hormone by chronic psychosocial stress , 1995, Psychoneuroendocrinology.

[2]  Gerwin Schalk,et al.  A Practical Guide to Brain–Computer Interfacing with BCI2000: General-Purpose Software for Brain-Computer Interface Research, Data Acquisition, Stimulus Presentation, and Brain Monitoring , 2010 .

[3]  I. Deary.  Measuring stress: A guide for health and social scientists , 1996 .

[4]  C. Aine.  A conceptual overview and critique of functional neuroimaging techniques in humans: I. MRI/FMRI and PET. , 1995, Critical reviews in neurobiology.

[5]  D B Newlin,et al.  EEG during masturbation and ejaculation , 1985, Archives of sexual behavior.

[6]  K Matsunami,et al.  Generator sources of EEG large waves elicited by mental stress of memory recall or mental calculation. , 2001, The Japanese journal of physiology.

[7]  Václav Snásel,et al.  Bars Problem Solving - New Neural Network Method and Comparison , 2007, MICAI.

[8]  John J. B. Allen,et al.  Frontal EEG asymmetry and premenstrual dysphoric symptomatology. , 2006, Journal of abnormal psychology.

[9]  Makoto Kato,et al.  Identifying neural components of emotion in free conversation with fMRI , 2011, 2011 Defense Science Research Conference and Expo (DSR).

[10]  Marius Crisan,et al.  Convergence and Hybrid Information Technologies , 2010 .

[11]  Neil Burgess,et al.  The theta rhythm , 2005, Hippocampus.

[12]  Martin T. Hagan,et al.  Neural network design , 1995 .

[13]  Lawrence R. Rabiner,et al.  On the use of autocorrelation analysis for pitch detection , 1977 .

[14]  Xuejing Sun,et al.  Pitch determination and voice quality analysis using Subharmonic-to-Harmonic Ratio , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[15]  Miroslav Voznak,et al.  Fundamental Frequency Extraction Method using Central Clipping and its Importance for the Classification of Emotional State , 2012 .

[16]  J GREEN.  Some observations on lambda waves and peripheral stimulation. , 1957, Electroencephalography and clinical neurophysiology.

[17]  T. Marczynski,et al.  Trait anxiety is reflected in EEG alpha response to stress. , 1981, Electroencephalography and clinical neurophysiology.

[18]  J. Stevens,et al.  Emotional activation of the electroencephalogram in patients with convulsive disorders. , 1959, The Journal of nervous and mental disease.

[19]  Stephen A. Zahorian,et al.  Yet Another Algorithm for Pitch Tracking , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[20]  Joseph Picone,et al.  Signal modeling techniques in speech recognition , 1993, Proc. IEEE.

[21]  Yuko Mizuno-Matsumoto,et al.  An fMRI study of brain processing related to stress states , 2012, World Automation Congress 2012.

[22]  Ryohei Nakatsu,et al.  Emotion Recognition in Speech Using Neural Networks , 2000, Neural Computing & Applications.

[23]  Seikwon Park,et al.  Relationship between Physiological Response and Salivary Cortisol Level to Life Stress , 2007 .

[24]  Sheldon Cohen,et al.  Psychological stress and disease. , 2007, JAMA.

[25]  Peter J. Lang,et al.  Affective engagement for facial expressions and emotional scenes: The influence of social anxiety , 2012, Biological Psychology.

[26]  M. L. Blair,et al.  Forebrain Pathways Mediating Stress-Induced Hormone Secretion , 1999, Frontiers in Neuroendocrinology.

[27]  Y. Stern,et al.  Increased sympathetic and decreased parasympathetic cardiovascular modulation in normal humans with acute sleep deprivation. , 2005, Journal of applied physiology.