Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Personality in speech : assessment and automatic classification
Polzehl T., Springer Publishing Company, Incorporated, New York, NY, 2014. 176 pp. Type: Book (978-3-319095-15-8)
Date Reviewed: Nov 12 2015

Utilizing computer technology to produce psychological assessments of personality traits is a developing field. The focus of this study, written by a researcher at Telekom Innovation Laboratories in Berlin, is speech. Researchers and innovators in human-computer interactions will find interesting and valuable interdisciplinary materials in these experiments.

The following list of chapter titles will help explain the contents: “Personality Assessment in Psychology,” “Speech-Based Personality Assessment,” “Database and Labeling,” “Analysis of Human Personality Perception,” “Automatic Personality Estimation,” “Discussion of the Results,” and “Conclusion and Outlook.”

The researcher began with an empirical psychological definition of personality as a “defined and measurable set of habitual patterns of behaviors, thoughts, and emotions.” Utilizing a professional speaker, two databases were recorded, one text-dependent and another text-independent. A third database consisted of non-acted realistic speech. Labeling sessions were conducted, utilizing the well-known NEO-FFI questionnaire, to assess the “Big 5” personality traits of openness, conscientiousness, extroversion, agreeableness, and neuroticism.

Detailed auto-processing and machine learning techniques were required to extract a number of speech characteristics. The automated signal-based classifications achieved 99 percent accuracy for the text-dependent database and 85.2 percent accuracy for the text-independent data. Detailed figures, tables, and statistics provide an appropriate level of explanation. The author indicates that future research needs to address the differences in predictive results, and that utilizing more questionnaires and refined speech feature extractions would be helpful.

While each chapter has a summary and list of references, there is no comprehensive index. However, detailed sectional divisions within the chapters, collected in the table of contents, will usually be adequate to rapidly aid the reader in finding the particular desired information. This is cutting-edge research with many potential applications.

Reviewer:  Brad Reid Review #: CR143939 (1601-0038)
Bookmark and Share
  Reviewer Selected
Featured Reviewer
 
 
Classifier Design And Evaluation (I.5.2 ... )
 
 
Interaction Styles (H.5.2 ... )
 
 
Speech Recognition And Synthesis (I.2.7 ... )
 
 
Learning (I.2.6 )
 
Would you recommend this review?
yes
no
Other reviews under "Classifier Design And Evaluation": Date
Linear discrimination with symmetrical models
Bobrowski L. Pattern Recognition 19(1): 101-109, 1986. Type: Article
Feb 1 1988
An application of a graph distance measure to the classification of muscle tissue patterns
Sanfeliu A. (ed), Fu K., Prewitt J. International Journal of Pattern Recognition and Artificial Intelligence 1(1): 17-42, 1987. Type: Article
Dec 1 1989
Selective networks and recognition automata
George N. J., Edelman G.  Computer culture: the scientific, intellectual, and social impact of the computer (, New York,2011984. Type: Proceedings
May 1 1987
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy