1 / 17

Acoustic/Prosodic and Lexical Correlates of Charismatic Speech

Acoustic/Prosodic and Lexical Correlates of Charismatic Speech. Andrew Rosenberg & Julia Hirschberg Columbia University Interspeech 2005 - Lisbon. Why study charismatic speech?. Construction of a feedback system for public speakers, (politicians, academic instructors, etc.)

Sophia
Télécharger la présentation

Acoustic/Prosodic and Lexical Correlates of Charismatic Speech

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Acoustic/Prosodic and Lexical Correlates of Charismatic Speech Andrew Rosenberg & Julia Hirschberg Columbia University Interspeech 2005 - Lisbon

  2. Why study charismatic speech? • Construction of a feedback system for public speakers, (politicians, academic instructors, etc.) • Identification of potential charismatic leaders • Automatic generation of “charismatic-like” speech

  3. What is charisma? • Not “closed door” or one-on-one charisma. • Rather, political (or religious) charisma • The ability to attract, and retain followers by virtue of personality as opposed to tradition or laws. (Weber) • E.g. Ghandi, Hitler, Castro. • Charismatic speech: Speech that encourages listeners to perceive the speaker as “charismatic”.

  4. Goals of this study • Determine to what degree subjects agree as to the charisma of a speaker. • Determine the existence and identify a functional definition of charisma. • Identify acoustic/prosodic and lexical properties of speech that communicate charisma

  5. Study Description • Subjects: Friends and colleagues, no incentive • Interface: Presentation of 45 short speech segments (2-30secs) via a web form • Dependent variables: 5-point Likert scale ratings of agreement on 26 statements about the speaker. • Duration: avg. 1.5 hrs, min 45m, max ~3hrs

  6. Study Description • Interface • http://www1.cs.columbia.edu/~amaxwell/survey/

  7. Study Description • Materials: 45 tokens of American political speech from late ’03 and early ‘04 • Speakers: 9 Candidates for Democratic Party’s nomination for President • Clark, Dean, Edwards, Gephardt, Kerry, Kucinich, Lieberman, Moseley Braun, Sharpton • Topics: Postwar Iraq, Healthcare, Bush’s Tax plan, Reason for Running, Content-Neutral

  8. How much do subjects agree with one another? • Using the weighted kappa statistic with quadratic weighting, mean  = 0.213 • Do subjects agree about what is charismatic? •  = 0.224 (8th) • Inter-subject agreement by token • No significant differences across all tokens • Inter-subject agreement by statement • The individual statements demonstrate significantly different agreements

  9. What do subjects mean by “charismatic”? • Using the kappa statistic determined which pairs of statements were most closely correlated with the charismatic statement.

  10. Does the identity of the speaker affect judgments of charisma? • There is a significant difference between speakers (p=1.75e-2) • Most charismatic • Rep. Edwards (3.73) • Rev. Sharpton (3.40) • Gov. Dean (3.32) • Least charismatic • Sen. Lieberman (2.38) • Rep. Kucinich (2.73) • Rep. Gephardt (2.77)

  11. Does the genre or topic of speech affect judgments of charisma? • The tokens were taken from debates, interviews, stump speeches, and a campaign ad • Stump speeches were the most charismatic. (3.28) • Interviews the least. (2.90) • Topic does not affect ratings of charisma.

  12. Does recognizing a speaker affect judgments of charisma? • Subjects were asked to identify which, if any, speakers they recognized at the end of the study. • Subjects rated recognized speakers (3.28) significantly more charismatic than those they did not (2.99).

  13. Duration (secs) Min, max, mean, stdev F0 Raw and normalized by speaker Min, max, mean, stdev intensity Number of intonational, intermediate, and internal phrases Mean and stdev of normalized F0 and intensity across phrases Speaking rate (syls/sec) Length (words, syllables) 1st, 2nd, 3rd person pronoun density Function to content word ratio Mean syllables/word Mean words per intermediate and intonational phrase What makes speech charismatic?Acoustic/Prosodic and Lexical Properties Examined

  14. What makes speech charismatic?Properties showing positive correlation with charisma • More Content • Length in secs, words, syllables, and phrases • Higher and more dynamic raw F0 • Min, max, mean, std. dev. of F0 over male speakers • Greater intensity • Mean intensity • Higher in a speaker’s pitch range • Mean normalized F0

  15. Faster speaking rate • Syllables per second • Greater variation of F0 and intensity across phrases • Std. dev. of normalized phrase F0 and intensity • The use of more first person pronouns • First person pronoun density • The use of polysyllabic words • Lexical complexity (mean syllables per word)

  16. Conclusions • There is substantial individual differences in subject perception of charisma. • There exists a common, functional definition of charisma. • Namely, “charismatic is enthusiastic, charming, convincing, persuasive, powerful and not boring” • Broadly, dynamic speech – loud, high in the pitch range – using first person pronouns is associated with charisma.

  17. Future Research • Isolate the lexical component of speech to determine the relative influences of what is said and how it is said. • Adjust acoustic/prosodic features to generate more/less charismatic speech • Study communication of charisma in other languages, specifically Palestinian Arabic.

More Related