Speech emotion detection

1
Speech emotion detection

• General architecture of a speech emotion
  detection system
• What features?

2
Local approach RFC TiltP. Taylor, The Tilt
Intonation Model, 1998

• Intonation events

• RFC Model(rise/fall/connection)?

• Tilt Model
• Amplitude
• Duration
• Tilt (shape)
• Problem automatic event labeling

3
Global approachBreazeal Aryananda, Recognition
of Affective Communicative Intent in
Robot-Directed Speech, 2002

• Features
• Pitch
• mean, variance, min, max, range,
• Energy
• mean, variance, min, max, range, mean/variance,
• Other
• pace, voiced percentage,
• Less precise, but more simple
• Problem needs training data!

4
Global approach (2)

• First idea
• Decision tree
• Data not very appropriate
• Difficult to configure
• Second idea
• Nearest neighbor
• With Mahalanobis distance

5
Implementation

• Edimburgh Speech Tools library (University of
  Edimburgh)? http//www.cstr.ed.ac.uk/projects/spe
  ech_tools/
• pitch tracking
• sound recording
• Online recognition

6
Results

• Only tested with one person
• Ok for sad and happy (100)
• More difficult for angry and neutral (60)
• Video