Personality in Speech: Assessment and Automatic Classification
This work combines interdisciplinary knowledge and experience from research fields of psychology, linguistics, audio-processing, machine learning, and computer science. The work systematically explores a novel research topic devoted to automated modeling of personality expression from speech. For this aim, it introduces a novel personality assessment questionnaire and presents the results of extensive labeling sessions to annotate the speech data with personality assessments. It provides estimates of the Big 5 personality traits, i.e. openness, conscientiousness, extroversion, agreeableness, and
neuroticism. Based on a database built on the questionnaire, the book presents models to tell apart different personality types or classes from speech automatically.
What people are saying - Write a review
We haven't found any reviews in the usual places.
2 SpeechBased Personality Assessment
3 Database and Labeling
4 Analysis of Human Personality Perception
5 Automatic Personality Estimation
6 Discussion of the Results
7 Conclusion and Outlook
Appendix A Label Distributions TextDependentRecordings
Appendix B Label Distributions TextIndependentRecordings
Other editions - View all
accuracy acted data agreeableness algorithm analyses applied audio descriptor groups automatic prediction bandwidth behavior Big Five calculated characteristics classification close-capture coefficients conscientiousness consistencies database dataset descriptor groups distribution experiments extracted extroversion features capturing five factor formants frequency high and low high targets human ratings IGR ranking IGR-ranked Features individual intensity inventory labels linear kernel linguistic loudness low targets machine learning mean Metze F MFCC models multi-speaker data NEO-FFI NEO-PI-R neuroticism non-linear normal distribution number of features observed overall parameters pauses perceived performance personality perceptions personality targets personality traits plot Polzehl presented prosodic Psychol psychology questionnaire raters regression respect RMSE RMSE resulted Sect segments shows speaker spectral speech recognition speech synthesis Stacked audio descriptor stand-alone microphone recordings statistics stimuli subset support vector support vector regression text-dependent data text-dependent recordings trait score prediction trait theory unvoiced vocal Voice Activity Detection voice quality voicedSeg wholeUtt