Spoken Cues to Deception

CS 4706
What is Deception?
 Defining Deception

• Deliberate choice to mislead a target

without prior notification
• To gain some advantage or to avoid some penalty
• Not:
– Self-deception, delusion
– Theater
– Falsehoods due to ignorance/error
– Pathological behavior
• NB: people typically tell at least 2 lies per day
 Who Studies Deception?

• Language and cognition

• Law enforcement practitioners:
– Police
– Military
– Jurisprudence
– Intelligence agencies
• Social services workers (SSA, Housing Authority)
• Business security officers
• Mental health professionals
• Political consultants
 Why is it hard to deceive?

• Increase in cognitive load if …

– Fabrication means keeping story straight
– Concealment means remembering what is omitted
• Fear of detection if …
– Target believed to be hard to fool
– Target believed to be suspicious
– Stakes are high: serious rewards and/or punishments
• Hard to control indicators of emotion/deception
• So deception detection may be possible….
 Potential Cues (cf. DePaulo ’03)

• Body posture and gestures (Burgoon et al ‘94)

– Complete shifts in posture, touching one’s face,…
• Microexpressions (Ekman ‘76, Frank ‘03)
– Fleeting traces of fear, elation,…
• Biometric factors (Horvath ‘73)
– Increased blood pressure, perspiration, respiration…
• Variation in what is said and how (Adams ‘96,
Pennebaker et al ‘01, Streeter et al ‘77)
– Contractions, lack of pronominalization, disfluencies,
slower response, mumbled words, increased or
decreased pitch range, less coherent, microtremors,…
 Potential Cues to Deception
(DePaulo et al. ’03)
• Liars less forthcoming? • Liars less positive, pleasant?
– - Talking time – - Cooperative
– - Details – + Negative, complaining
– + Presses lips – - Facial pleasantness
• Liars less compelling? • Liars more tense?
– - Plausibility – + Nervous, tense overall
– - Logical Structure – + Vocal tension
– - Discrepant, ambivalent – + F0
– - Verbal, vocal involvement – + Pupil dilation
– - Illustrators – + Fidgeting
– - Verbal, vocal immediacy
• Fewer ordinary imperfections?
– + Verbal, vocal uncertainty
– - Spontaneous corrections
– + Chin raise
– - Admitted lack of memory
– + Word, phrase repetitions
– + Peripheral details
 Potential Spoken Cues to Deception
(DePaulo et al. ’03)
• Liars less forthcoming? • Liars less positive, pleasant?
– - Talking time – - Cooperative
– - Details – + Negative, complaining
– + Presses lips – - Facial pleasantness
• Liars less compelling? • Liars more tense?
– - Plausibility – + Nervous, tense overall
– - Logical Structure – + Vocal tension
– - Discrepant, ambivalent – + F0
– - Verbal, vocal involvement – + Pupil dilation
– - Illustrators – + Fidgeting
– - Verbal, vocal immediacy
• Fewer ordinary imperfections?
– + Verbal, vocal uncertainty
– - Spontaneous corrections
– + Chin raise
– - Admitted lack of memory
– + Word, phrase repetitions
– + Peripheral details
 Previous Approaches to Deception Detection

• John Reid & Associates

– Behavioral Analysis: Interview and Interrogation
• Polygraph
– http://antipolygraph.org
– The Polygraph and Lie Detection (N.A.P. 2003)
• Voice Stress Analysis
– Microtremors 8-12Hz
– No real evidence
• Nemesysco and the Love Detector
 Newer Techniques for Automatic Analysis

• Most previous deception studies focus on

– Visual or biometric behaviors
– A few, hand-coded or perception-based cues
• Our goal: Identify a set of acoustic, prosodic, and
lexical features that distinguish between deceptive
and non-deceptive speech
– As well or better than human judges
– Using automatic feature-extraction
– Using Machine Learning techniques to identify best-
performing features and create automatic predictors
 Our Approach
• Record a new corpus of deceptive/non-deceptive
speech and transcribe it
• Use automatic speech recognition (ASR)
technology to perform forced alignment on
transcripts
• Extract acoustic, prosodic, and lexical features
based on previous literature and our work in
emotional speech and speaker id
• Use statistical Machine Learning techniques to
train models to distinguish deceptive from non-
deceptive speech
– Rule induction (Ripper), CART trees, SVMs
 Major Obstacles

• Corpus-based approaches require large amounts of

training data – ironically difficult for deception
– Differences between real world and laboratory lies
• Motivation and consequences
• Recording conditions
• Assessment of ground truth
• Ethical issues
– Privacy
– Subject rights and Institutional Review Boards
 Columbia/SRI/Colorado Deception Corpus
(CSC)
• Deceptive and non-deceptive speech
– Within subject (32 adult native speakers)
– 25-50m interviews
• Design:
– Subjects told goal was to find “people similar to the ‘25
top entrepreneurs of America’”
– Given tests in 6 categories (e.g. knowledge of food and
wine, survival skills, NYC geography, civics, music), e.g.
• “What should you do if you are bitten by a poisonous
snake out in the wilderness?”
• “Sing Casta Diva.”
• “What are the 3 branches of government?”
 – Questions manipulated so scores always differed from a
(fake) entrepreneur target in 4/6 categories
– Subjects then told real goal was to compare those who
actually possess knowledge and ability vs. those who
can “talk a good game”
– Subjects given another chance at $100 lottery if they
could convince an interviewer they match target
completely
• Recorded interviews
– Interviewer asks about overall performance on each test
with follow-up questions (e.g. “How did you do on the
survival skills test?”)
– Subjects also indicate whether each statement T or F by
pressing pedals hidden from interviewer
 The Data

• 15.2 hrs. of interviews; 7 hrs subject speech

• Lexically transcribed & automatically aligned
• Truth conditions aligned with transcripts: Global / Local
• Segmentations (Local Truth/Local Lie):
– Words (31,200/47,188)
– Slash units (5709/3782)
– Prosodic phrases (11,612/7108)
– Turns (2230/1573)
• 250+ features
– Acoustic/prosodic features extracted from ASR transcripts
– Lexical and subject-dependent features extracted from
orthographic transcripts
 Acoustic/Prosodic Features

• Duration features
– Phone / Vowel / Syllable Durations
– Normalized by Phone/Vowel Means, Speaker
• Speaking rate features (vowels/time)
• Pause features (cf Benus et al ‘06)
– Speech to pause ratio, number of long pauses
– Maximum pause length
• Energy features (RMS energy)
• Pitch features
– Pitch stylization (Sonmez et al. ‘98)
– Model of F0 to estimate speaker range
– Pitch ranges, slopes, locations of interest
• Spectral tilt features
 Lexical Features
• Presence and # of filled pauses • Presence of hedges
• Is this a question? A question • Complexity: syls/words
following a question
• Presence of pronouns (by • Number of repeated words
person, case and number) • Punctuation type
• A specific denial? • Length of unit (in sec and
• Presence and # of cue phrases words)
• Presence of self repairs
• # words/unit length
• Presence of contractions
• Presence of positive/negative • # of laughs
emotion words • # of audible breaths
• Verb tense
• # of other speaker noise
• Presence of ‘yes’, ‘no’, ‘not’,
negative contractions • # of mispronounced words
• Presence of ‘absolutely’, ‘really’ • # of unintelligible words
 Subject-Dependent Features: Calibrating
Truthful Behavior
• % units with cue phrases
• % units with filled pauses
• % units with laughter
• Ratio lies with filled pauses/truths with filled
pauses
• Ratio lies with cue phrases/truths with filled
pauses
• Ratio lies with laughter / truths with laughter
• Gender
 Columbia University– SRI/ICSI – University of Colorado
Deception Corpus: An Example Segment
SEGMENT TYPE
Breath Group
LABEL
Obtained LIE
from subject
pedal presses.

um i was visiting a friend in venezuela and we went camping

ACOUSTIC FEATURES
max_corrected_pitch 5.7 pitch_change_last_word -11.5
mean_corrected_pitch 5.3 normalized_mean_energy 0.2
Produced
pitch_change_1st_word -6.7 unintelligible_words 0.0
Produced using automaticall
ASR output y
and other using lexical
LEXICAL FEATURES
acoustic transcription
analyses has_filled_pause YES negative_emotion_word NO .
positive_emotion_word YES contains_pronoun_i YES
uses_past_tense NO verbs_in_gerund YES

PREDICTION
LIE
 CSC Corpus: Results
• Classification via Ripper rule induction, randomized 5-fold
xval)
– 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 correlations — varies with subject
 But…How Well Do Humans Do?

• Most people are very poor at detecting deception

– ~50% accuracy (Ekman & O’Sullivan ‘91, Aamodt ‘06)
– People use unreliable cues
– Even with training
A Meta-Study of Human Deception Detection
(Aamodt & Mitchell 2004)

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
A Meta-Study of Human Deception Detection
(Aamodt & Mitchell 2004)

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
 Comparing Human and Automatic Deception
Detection
• Deception detection on the CSC Corpus
• 32 Judges
– Each judge rated 2 interviews
– Rated local and global lies
– Received ‘training’ on one subject.
• Pre- and post-test questionnaires
• Personality Inventory
 By Judge
58.2% Acc.

By Interviewee
 Personality Measure: NEO-FFI

• Costa & McCrae (1992) Five-factor model

– Extroversion (Surgency). Includes traits such as
talkative, energetic, and assertive.
– Agreeableness. Includes traits like sympathetic, kind,
and affectionate.
– Conscientiousness. Tendency to be organized,
thorough, and planful.
– Neuroticism (reversed as Emotional Stability).
Characterized by traits like tense, moody, and anxious.
– Openness to Experience (aka Intellect or
Intellect/Imagination). Includes having wide interests,
and being imaginative and insightful.
 Neuroticism, Openness & Agreeableness
correlate with judge performance

WRT Global lies.

 Other 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 reported using disfluencies as cues
to deception
– But in this corpus, disfluencies correlate with truth
(Benus et al. ‘06)
 Future Research

• Looking for objective, independent correlates of

individual differences in deception behaviors
– Particular acoustic/prosodic styles
– Personality factors
• New data collection to associate personality type
with vocal behaviors
• Critical for the future
– Examining cultural differences in deception
 Next
• Charismatic Speech