Deceptive Speech

1
Deceptive Speech

• Frank Enos April 19, 2006

2
Defining Deception

• Deliberate choice to mislead a target without
  prior notification (Ekman01)
• Often to gain some advantage
• Excludes
• Self-deception
• Theater, etc.
• Falsehoods due to ignorance/error
• Pathological behaviors

3
Why study deception?

• Law enforcement / Jurisprudence
• Intelligence / Military / Security
• Business
• Politics
• Mental health practitioners
• Social situations
• Is it ever good to lie?

4
Why study deception?

• What makes speech believable?
• Recognizing deception means recognizing
  intention.
• How do people spot a liar?
• How does this relate to other subjective
  phenomena in speech? E.g. emotion, charisma

5
Problems in studying deception?

• Most people are terrible at detecting deception
  50 accuracy (Ekman Osullivan 1991, Aamodt
  2006, etc.)
• People use subjective judgments emotion, etc.
• Recognizing emotion is hard

6
People Are Terrible At This
Group Studies Subjects Accuracy
Criminals 1 52 65.40
Secret service 1 34 64.12
Psychologists 4 508 61.56
Judges 2 194 59.01
Cops 8 511 55.16
Federal officers 4 341 54.54
Students 122 8,876 54.20
Detectives 5 341 51.16
Parole officers 1 32 40.42
7
Problems in studying deception?

• Hard to get good data
• Real world (example)
• Laboratory
• Ethical issues
• Privacy
• Subject rights
• Claims of success
• But also ethical imperatives
• Need for reliable methods
• Debunking faulty methods
• False confessions

8
20th Century Lie Detection

• Polygraph
• http//antipolygraph.org
• The Polygraph and Lie Detection (N.A.P. 2003)
• Voice Stress Analysis
• Microtremors 8-12Hz
• Universal Lie response
• http//www.love-detector.com/
• http//news-info.wustl.edu/news/page/normal/669.ht
  ml
• Reid
• Behavioral Analysis Interview
• Interrogation

9
Frank Tells Some Lies
An Example
10
Frank Tells Some Lies

• Maria Im buying tickets to Händels Messiah for
  me and my friends would you like to join us?
• Frank When is it?
• Maria December 19th.
• Frank Uh the 19th
• Maria My two friends from school are coming, and
  Robin
• Frank Id love to!

11
How to Lie (Ekman01)

• Concealment
• Falsification
• Misdirecting
• Telling the truth falsely
• Half-concealment
• Incorrect inference dodge.

12
Frank Tells Some Lies

• Maria Im buying tickets to Handels Messiah for
  me and my friends would you like to join us?
• Frank When is it?
• Maria December 19th.
• Frank Uh the 19th
• Maria My two friends from school are coming,
  and Robin
• Frank Id love to!

13
Reasons To Lie (Frank92 )

• Self-preservation
• Self-presentation
• Gain
• Altruistic (social) lies

14
How Not To Lie (Ekman01)

• Leakage
• Part of the truth comes out
• Liar shows inconsistent emotion
• Liar says something inconsistent with the lie
• Deception clues
• Indications that the speaker is deceiving
• Again, can be emotion
• Inconsistent story

15
How Not To Lie (Ekman01)

• Bad lines
• Lying well is hard
• Fabrication means keeping story straight
• Concealment means remembering what is omitted
• All this creates cognitive load ? harder to hide
  emotion
• Detection apprehension (fear)
• Target is hard to fool
• Target is suspicious
• Stakes are high
• Serious rewards and/or punishments are at stake
• Punishment for being caught is great

16
How Not To Lie (Ekman01)

• Deception guilt
• Stakes for the target are high
• Deceit is unauthorized
• Liar is not practiced at lying
• Liar and target are acquainted
• Target cant be faulted as mean or gullible
• Deception is unexpected by target
• Duping delight
• Target poses particular challenge
• Lie is a particular challenge
• Others can appreciate liars performance

17
Features of Deception

• Cognitive
• Coherence, fluency
• Interpersonal
• Discourse features DA, turn-taking, etc.
• Emotion

18
Describing Emotion

• Primary emotions
• Acceptance, anger, anticipation, disgust, joy,
  fear, sadness, surprise
• One approach continuous dim. model
  (Cowie/Lang)
• Activation evaluation space
• Add control/agency
• Primary Es differ on at least 2 dimensions of
  this scale (Pereira)

19
Problems With Emotion and Deception

• Relevant emotions may not differ much on these
  scales
• Othello error
• People are afraid of the police
• People are angry when wrongly accused
• People think pizza is funny
• Brokow hazard
• Failure to account for individual differences

20
Bulk of extant deception research

• Not focused on verifying 20th century techniques
• Done by psychologists
• Considers primarily facial and physical cues
• Speech is hard
• Little focus on automatic detection of deception

21
Modeling Deception in Speech

• Lexical
• Prosodic/Acoustic
• Discourse

22
Deception in Speech (Depaulo 03)

• Positive Correlates
• Interrupted/repeated words
• References to external events
• Verbal/vocal uncertainty
• Vocal tension
• F0

23
Deception in Speech (Depaulo 03)

• Negative Correlates
• Subject stays on topic
• Admitted uncertainties
• Verbal/vocal immediacy
• Admitted lack of memory
• Spontaneous corrections

24
Problems, revisited

• Differences due to
• Gender
• Social Status
• Language
• Culture
• Personality

25
Columbia/SRI/Colorado Corpus

• With Julia Hirschberg, Stefan Benus, and
  colleagues from SRI/ICSI and U. C. Boulder
• Goals
• Examine feasibility of automatic deception
  detection using speech
• Discover or verify acoustic/prosodic, lexical,
  and discourse correlates of deception
• Model a non-guilt scenario
• Create a clean corpus

26
Columbia/SRI/Colorado Corpus

• Inflated-performance scenario
• Motivation financial gain and self-presentation
• 32 Subjects 16 women, 16 men
• Native speakers of Standard American English
• Subjects told study seeks to identify people who
  match profile based on 25 Top Entrepreneurs

27
Columbia/SRI/Colorado Corpus

• Subjects take test in six categories
• Interactive, music, survival, food, NYC
  geography, civics
• Questions manipulated ?
• 2 too high 2 too low 2 match
• Subjects told study also seeks people who can
  convince interviewer they match profile
• Self-presentation reward
• Subjects undergo recorded interview in booth
• Indicate veracity of factual content of each
  utterance using pedals

28
CSC Corpus Data

• 15.2 hrs. of interviews 7 hrs subject speech
• Lexically transcribed automatically aligned ?
  lexical/discourse features
• Lie conditions Global Lie / Local Lie
• Segmentations (LT/LL) slash units (5709/3782),
  phrases (11,612/7108), turns (2230/1573)
• Acoustic features ( recognizer output)

29
(No Transcript)
30
Columbia University SRI/ICSI University of
Colorado Deception Corpus An Example Segment
Breath Group
SEGMENT TYPE
LABEL
LIE
Obtained from subject pedal presses.
um i was visiting a friend in venezuela and we
went camping
ACOUSTIC FEATURES
max_corrected_pitch 5.7 mean_corrected_pitch 5.3 p
itch_change_1st_word -6.7
pitch_change_last_word
-11.5 normalized_mean_energy 0.2 unintelligible_w
ords 0.0
Produced using ASR output and other acoustic
analyses
Produced automatically using lexical transcriptio
n.
LEXICAL FEATURES
has_filled_pause YES positive_emotion_word
YES uses_past_tense NO
negative_emotion_word NO contains_pronoun_i YES
verbs_in_gerund YES
LIE
PREDICTION
31
CSC Corpus Results

• Classification (Ripper rule induction,
  randomized 5-fold cv)
• Slash Units / Local Lies Baseline 60.2
• Lexical acoustic 62.8 subject dependent
  66.4
• Phrases / Local Lies Baseline 59.9
• Lexical acoustic 61.1 subject dependent
  67.1
• Other findings
• Positive emotion words? deception (LIWC)
• Pleasantness ? deception (DAL)
• Filled pauses ? truth
• Some pitch correlation varies with subject

32
Example JRIP rules (cueLieToCueTruths gt 2)
and (TOPIC topic_newyork) and
(numSUwithFPtoNumSU lt 0) and (wu_ENERGY_NO_UV_STY
_MAX__EG_ZNORM-ENERGY_NO_UV_STY_MIN__EG_ZNORM-D
lt 5.846) gt PEDALL (231.0/61.0) (cueLieToCueTr
uths gt 2) and (numSUwithFPtoNumSU lt 1) and
(wu_ENERGY_NO_UV_STY_MAX__EG_ZNORM-ENERGY_NO_UV_ST
Y_MIN__EG_ZNORM-D lt 5.68314) and
(wu_ENERGY_NO_UV_RAW_MAX-ENERGY_NO_UV_RAW_MIN-D
gt 8.41605) and (wu_F0_SLOPES_NOHD__LAST gt
-2.004) gt PEDALL (284.0/117.0) (cueLieToCueTru
ths gt 2) and (wu_F0_RAW_MAX gt 5.706379) and
(wu_DUR_PHONE_SPNN_AV lt 1.0661) gt PEDALL
(262.0/115.0)
33
CSC Corpus A Perception Study

• With Julia Hirschberg, Stefan Benus, Robin Cautin
  and colleagues from SRI/ICSI
• 32 Judges
• Each judge rated 2 interviews
• Judge Labels
• Local Lie using Praat
• Global Lie on paper
• Takes pre- and post-test questionnaires
• Personality Inventory
• Judge receives training on one subject.

34
By Judge 58.2 Acc.
By Interviewee
35
Personality Measure NEO-FFI

• Costa McCrae (1992) Five-factor model
• Openness to Experience
• Conscientiousness
• Extraversion
• Agreeability
• Neuroticism
• Widely used in psychology literature

36
Neuroticism, Openness Agreeableness correlate
with judge performance
WRT Global lies.
37
These factors also provide strongly predictive
models for accuracy at global lies.
38
Other Perception Findings

• No effect for training
• Judges post-test confidence did not correlate
  with pre-test confidence
• Judges who claimed experience had significantly
  higher pre-test confidence
• But not higher accuracy!
• Many subjects used disfluencies as cues to D.
• In this corpus, disfluencies correlate with
  TRUTH! (Benus et al. 06)

39
Our Future Work

• Individual differences
• Wizards of deception
• Predicting Global Lies
• Local lies as hotspots
• New paradigm
• Shorter
• Addition of personality test for speakers
• Addition of cognitive load