Back Channel Communication

1
Back Channel Communication

• Antoine Raux
• Dialogs on Dialogs 02/25/2005

2
Outline

• From Back Channel to backchannels
• Function of the Back Channel
• Characteristics of the Back Channel
• The Back Channel in Spoken Dialogue Systems

3
From back channel

• 70s Conversation Analysts attempt to describe
  systematic rules for turn-taking management
• Goal minimize gaps and overlaps between speakers
• BUT many overlaps in natural speech
• E.g. mm-hmm, okay, yeah
• Back channel (Yngve 1970) Parallel channel for
  communication (Duncan 1972)
• Back channel communication does not constitute a
  turn or a claim for a turn
• But it may participate in a variety of
  communication functions, including the regulation
  of speaking turns.

4
to backchannels

• Backchannel listener-produced signal such as
  mm-hmm, yeah(To backchannel to produce
  such signals)
• Does not imply the will to take the turn
• Implies some form of acknowledgment (in general)

5
Front vs Back Channel
Front Channel Back Channel
Function Propositional Transactional Conversation managmt Social Conversation managmt Social
Protocol Turn-takingFloor sharing ? (controlled by FC?)No floor to share
Lexical content Anything vocalizations, short words, phrases (Thats true)
6
Front-channel cues to back-channel signals

• Koiso et al (1998)
• Analyze the relationship between different
  syntactic and prosodic features and the
  occurrence of backchannels

7
Koiso et al (Methodology)

• Data 8 dialogs from Japanese Map Task corpus
• replica of the Edinburgh MT
• Face-to-face and speech only (no difference)
• Features
• Syntactic POS
• Duration of last mora (normal/long/short)
• F0 pattern of last mora (flat-fall, rise)
• Peak F0 (low/high)
• Energy pattern (late-decr, decr, no-decr)
• Peak energy (low/high)

8
Koiso et al (Results)

• Frequency of feature values

BC gt no-BC POSverb-phrase, post-position, conjunction F0 patflat-fall or rise-fallEnergy patlate-decr Peak energyhigh no-BC gt BC POSadv, conjunction, interjection, filler Durshort F0 patfall or flat Energy patnon-decr Peak energylow
9
Koiso et al (Results)

• Decision Tree analysis
• Compare the loss in performance by not using each
  feature
• POS single best feature
• Prosodic features altogether as good as POS

10
Koiso et al (Discussion)

• Some POS strongly inhibit BC
• Individual prosodic features are not good
  indicators of BC occurrence
• BC occurrence is conditioned by both POS and
  prosody (as a whole)
• What about other languages?
• What about BC overlapping with speech?

11
BC cues in English and Japanese

• Ward and Tsukahara (2000)
• Tests one hypothesis (BC are triggered by low
  pitch cues) for two languages

12
The Low Pitch Cue

• Both in American English and Japanese, it appears
  that after a region of low pitch lasting 110 ms
  the listener tends to produce back-channel
  feedback.
• Goal of this paper quantitatively test this on
  naturally occurring conversations

13
Ward and Tsukahara (Methodology)

• Data
• English 8 conversations, 12 speakers (first
  author participates in 5 conversations!)
• Japanese 18 conversations, 24 speakers
• Prediction
• Every 10ms decide BC/no-BC by applying a hand
  coded rule with 5 parameters tuned to the data

14
Ward and Tsukahara (Results)

• Each predicted BC was considered correct if it
  fell within 500ms of an actual BC
• Low pitch region rule is better than chance both
  in English and Japanese

15
Ward and Tsukahara (Results)

• Issues
• Evaluation (tolerance window size, speakers
  produce BCs with different frequencies)
• No actual comparison between languages
• Are low pitch regions and BCs simply correlated
  to other phenomena (syntactic completion,
  disfluencies) or is there a direct
  cause/consequence relationship?

16
Effects of Native Language and Gender on BC

• Feke (2003)
• Conversation Analysis study of BC in
  native-English and native-Spanish, same- and
  mixed-gender dialogs

17
Definition of BC

• BC responses of the participant that is clearly
  not holding the floor
• Very loose compared to previous papers
• e.g. How did you find Quechua? is a BC
• Distinguishes In-Between BC and Overlap BC

18
Feke (Methodology)

• Recorded 8 non-scripted conversations between 8
  different speakers (2 native languages x 2
  genders x 2 subjects)
• Manually coded In-Between BCs and Overlap BCs

19
Feke (Results)

• No differences observed across cultures
• Participants of both genders tend to use more BC
  when conversing with someone of the opposite
  gender
• Difference seems bigger for females than for males

20
Feke (Discussion)

• Interesting/surprising result from the
  ethnological/sociological point of view
• Very few data points, no significance analysis
• Only looked at number of BCs
• Consequences on SDS? (e.g. using gender
  information in BC prediction, selecting the
  gender of an agent)

21
BC in Practical Systems

• Takeuchi et al (2003)
• Method to determine the timing of turn
  transitions and aizuchi (BC) on Japanese
  Human-Human corpus

22
Takeuchi (Approach)

• Similar to Koiso et al, but only using
  automatically extracted features
• Every 100 ms decide between
• Take turn
• Aizuchi (BC)
• Leave turn (wait)

23
Takeuchi (Approach)

• Decision Tree using
• Syntax (POS, content/function words)
• Utterance duration
• Pause duration/pause since last content wd
• Content word duration
• F0
• Power

24
Takeuchi (Results)

• Precision/Recall of frame classification
• Around 80 on the training set
• Less then 50 on a test set
• Subjective evaluation
• Artificially insert BC at predicted time
• Timing was judged good in 70-80
• On real utterances 72 (!)

25
Takeuchi (Discussion)

• Found that syntactic information did not help
  (contradicts Koiso?)
• Underscores the difficulty of evaluating
  turn-taking/backchanneling systems

26
Conclusion

• Hard to account for simultaneous turns in
  conversation
• Back Channel framework offers one explanation
• But most work remains very specific
• Missing a good theory of conversation