Automatic Speaker Verification : Technologies, Evaluations and Possible Future

1
Automatic Speaker Verification Technologies,
Evaluationsand Possible Future
Biometrics in Current Security Environments

• Gérard CHOLLET
• CNRS-LTCI, GET-ENST
• chollet_at_tsi.enst.fr

2
Outline

• State of affairs (tasks, security, forensic,)
• Speaker characteristics in the speech signal
• Automatic Speaker Verification
• Decision theory
• Text dependent / Text independent
• Imposture (occasional, dedicated)
• Voice transformations
• Audio-visual speaker verification
• Evaluations (algorithms, field tests, ergonomy,)
• Conclusions, Perspectives

3
Why should a computer recognize who is speaking ?

• Protection of individual property (habitation,
  bank account, personal data, messages, mobile
  phone, PDA,...)
• Limited access (secured areas, data bases)
• Personalization (only respond to its masters
  voice)
• Locate a particular person in an audio-visual
  document (information retrieval)
• Who is speaking in a meeting ?
• Is a suspect the criminal ? (forensic
  applications)

4
Tasks in Automatic Speaker Recognition

• Speaker verification (Voice Biometric)
• Are you really who you claim to be ?
• Identification (Speaker ID)
• Is this speech segment coming from a known
  speaker ?
• How large is the set of speakers (population of
  the world) ?
• Speaker detection, segmentation, indexing,
  retrieval, tracking
• Looking for recordings of a particular speaker
• Combining Speech and Speaker Recognition
• Adaptation to a new speaker, speaker typology
• Personalization in dialogue systems

5
Applications

• Access Control
• Physical facilities, Computer networks, Websites
• Transaction Authentication
• Telephone banking, e-Commerce
• Speech data Management
• Voice messaging, Search engines
• Law Enforcement
• Forensics, Home incarceration

6
Voice Biometric

• Avantages
• Often the only modality over the telephone,
• Low cost (microphone, A/D), Ubiquity
• Possible integration on a smart (SIM) card
• Natural bimodal fusion speaking face
• Disadvantages
• Lack of discretion
• Possibility of imitation and electronic imposture
• Lack of robustness to noise, distortion,
• Temporal drift

7
Speaker Identity in Speech

• Differences in
• Vocal tract shapes and muscular control
• Fundamental frequency (typical values)
• 100 Hz (Male), 200 Hz (Female), 300 Hz (Child)
• Glottal waveform
• Phonotactics
• Lexical usage
• The differences between Voices of Twins is a
  limit case
• Voices can also be imitated or disguised

8
(No Transcript)
9
Acoutic features

• Short term spectral analysis

10
Intra- and Inter-speaker variability
11
Speaker Verification

• Typology of approaches (EAGLES Handbook)
• Text dependent
• Public password
• Private password
• Customized password
• Text prompted
• Text independent
• Incremental enrolment
• Evaluation

12
History of Speaker Recognition
13
Current approaches
14
HMM structure depends on the application
15
Gaussian Mixture Model

• Parametric representation of the probability
  distribution of observations

16
Gaussian Mixture Models
8 Gaussians per mixture
17
Decision theory for identity verification

• Two types of errors
• False rejection (a client is rejected)
• False acceptation (an impostor is accepted)
• Decision theory given an observation O and a
  claimed identity
• H0 hypothesis it comes from an impostor
• H1 hypothesis it comes from our client
• H1 is chosen if and only if P(H1O) gt P(H0O)
  
• which could be rewritten (using Bayes law) as

18
Signal detection theory
19
Decision
20
Distribution of scores
21
Detection Error Tradeoff (DET) Curve
22
Evaluation

• Decision cost (FA, FR, priors, costs,)
• Receiver Operating Characteristic Curve
• Reference systems (open software)
• Evaluations (algorithms, field trials, ergonomy,)

23
National Institute of Standards Technology
(NIST)Speaker Verification Evaluations

• Annual evaluation since 1995
• Common paradigm for comparing technologies

24
NIST evaluations Results
25
Combining Speech Recognition and Speaker
Verification.

• Speaker independent phone HMMs
• Selection of segments or segment classes which
  are speaker specific
• Preliminary evaluations are performed on the NIST
  extended data set (one hour of training data per
  speaker)

26
ALISP data-driven speech segmentation
27
Searching in client and world speech dictionaries
for speaker verification purposes
28
Fusion
29
Fusion results
30
Speaking Faces Motivations

• A person speaking in front of a camera offers 2
  modalities for identity verification (speech and
  face).
• The sequence of face images and the
  synchronisation of speech and lip movements could
  be exploited.
• Imposture is much more difficult than with single
  modalities.
• Many PCs, PDAs, mobile phones are equiped with a
  camera. Audio-Visual Identity Verification will
  offer non-intrusive security for e-commerce,
  e-banking,

31
Talking Face Recognition(hybrid verification)
32
Lip features

• Tracking lip movements

33
A talking face model

• Using Hidden Markov Models (HMMs)

34
Morphing, avatars
35
Conclusions, Perspectives

• Deliberate imposture is a challenge for speech
  only systems
• Verification of identity based on features
  extracted from talking faces should be developped
• Common databases and evaluation protocols are
  necessary
• Free access to reference systems will facilitate
  future developments