Turn-Taking and Diarization

No suppression signals

• No suppression signals
• Why does she do this?
• Speech training before election?
• Why is she still perceived as domineering?
• When interrupted she doesn’t cede the floor despite lengthy stretches of simultaneous speech

Today

• Turn-taking behaviors in human-human conversation
• Task/circumstance dependencies
• Conversational Analysis
• Linguistic/cultural differences
• How do we take and give up turns?
• Diarization: Automatic Turn Segmentation

Diarization: Automatic Speaker Identification/Segmentation

• Segment audio corpora (Broadcast News, meetings, telephone conversations) into speaker segments
• Speaker segmentation
• Speaker identification
• Speech and music
• Speaker segmentation (Diarization)
• Initial segmentation
• Segment clustering based on acoustic features
• State-of-the-art: 8.47% error

Speaker identification

• Speaker identification
• Linguistic information to identify speaker types and speaker names (LIMSI ’04)
• Templates (“ has this report from ”)
• Results: 10.9% error on test set
• But only 10% of segments contain relevant patterns
• Estimate 25% error on broadcast news if segmentation and clustering is done to id all of each speaker’s segments

• CNN19980104.1130.0000
• MISCELLANEOUS TEXT (automatic initial)
• 01/04/1998 11:30:00.00
• in northern kentucky are forcing 3,000 people in two states to flee their
• homes.
• the fire started early this morning at the cargill company plant in
• maysville near the ohio river.
• authorities have been going door-to-door advising people in kentucky and
• ohio to take shelter in area high schools.
• the fire is in a building where several fertilizers and chemicals are
• stored.