BackchannelInviting Cues in TaskOriented Dialogue Agustn Gravano 1
Backchannel-Inviting Cues in Task-Oriented Dialogue Agustín Gravano 1, 2 Julia Hirschberg 1 (1) Columbia University, New York, USA (2) Universidad de Buenos Aires, Argentina
Introduction Interactive Voice Response Systems • Quickly spreading. Mostly simple functionality. • “Uncomfortable”, “awkward”. • ASR+TTS account for most IVR problems. • As ASR and TTS improve, other problems revealed. • Coordination of system-user exchanges. • Backchannels. Agustín Gravano Interspeech 2009 2
Introduction Backchannels • Short expressions uttered by listeners to: • Convey that they are paying attention. • Encourage the speaker to continue. • Examples: okay, uh-huh, mm-hm, alright. • Very frequent in task-oriented dialogue. • Thus, modeling human usage of BC should lead to an improved system-user coordination. Agustín Gravano Interspeech 2009 3
Introduction Goal • Learn when backchannels are likely to occur. • Find “backchannel-inviting” cues. • Cues displayed by the speaker “inviting” the listener to produce a backchannel response. • This could improve the coordination of IVRs: • Speech understanding: Detect points in the user’s turn where a backchannel would be welcome. • Speech generation: Display cues inviting the user to produce a backchannel. Agustín Gravano Interspeech 2009 4
Talk Outline • • • Previous work Material Method Results Conclusions Agustín Gravano Interspeech 2009 5
Backchannel-Inviting Cues Previous Work • Duncan 1972, 1973, 1974, inter alia. • Hypothesized six turn-yielding cues in face-to-face dialogue. • Several studies continued this line of research, but always excluded backchannels. • Ward & Tsukahara 2000. • Region of low pitch lasting 110 ms or more. • Cathcart et al. 2003. • Language model based on pause duration and part-ofspeech tags to predict the location of BC. Agustín Gravano Interspeech 2009 6
Material Columbia Games Corpus • • 12 task-oriented spontaneous dialogues. Standard American English. 13 subjects: 6 female, 7 male. Series of collaborative computer games. No eye contact. No speech restrictions. 9 hours of dialogue. Manual orthographic transcription, alignment. Manual prosodic annotations (To. BI). Agustín Gravano Interspeech 2009 7
Material Columbia Games Corpus Player 1: Describer Agustín Gravano Player 2: Follower Interspeech 2009 8
Backchannel-Inviting Cues • Cues displayed by the speaker “inviting” the listener to produce a backchannel response. Agustín Gravano Interspeech 2009 9
Backchannel-Inviting Cues Method • IPU (Inter Pausal Unit): Maximal sequence of words from the same speaker surrounded by silence ≥ 50 ms. Hold Speaker A: IPU 1 Backchannel IPU 4 IPU 2 IPU 3 Speaker B: • 3 trained annotators identified Backchannels using a labeling scheme described in [Gravano et al. 2007]. • To find BC-inviting cues, we compare: • IPUs preceding Holds, • IPUs preceding Backchannels. Agustín Gravano Interspeech 2009 10
Backchannel-Inviting Cues Individual Cues 1. Final rising intonation: 81% of IPUs before BC end in H-H% or L-H%. 2. 3. 4. 5. 6. } Higher pitch level. • entire IPU • final 1. 0 sec Higher intensity level. • final 0. 5 sec Lower NHR (voice quality). Longer IPU duration (seconds, #words). Final POS bigram: 72% of IPUs before BC end in DT NN, JJ NN, or NN NN. Agustín Gravano Interspeech 2009 11
Backchannel-Inviting Cues Defining Presence of a Cue • 2 representative features for each cue: Final intonation Pitch slope over final 200 ms, 300 ms. Intensity level Mean intensity over final 500 ms, 1000 ms. Pitch level Mean pitch over final 500 ms, 1000 ms. Voice quality NHR over final 500 ms, 1000 ms. IPU duration Duration in ms, and in number of words. Final POS bigram {‘DT NN’, ‘JJ NN’, ‘NN NN’} vs. Rest (binary). • Define presence/absence based on whether the value is closer to the mean before BC or H. Agustín Gravano Interspeech 2009 12
Top Frequencies of Complex Cues digit == cue present dot == cue absent BC-inviting cues: 1: Final intonation 2: Intensity level 3: Pitch level 4: IPU duration 5: Voice quality 6: Final POS bigram Agustín Gravano Interspeech 2009 13
Backchannel-Inviting Cues Percentage of IPUs followed by a BC Combined Cues r 2 = 0. 993 Number of cues conjointly displayed Agustín Gravano Interspeech 2009 14
Backchannel-Inviting Cues IVR Systems • After each IPU from the user: if estimated likelihood > threshold then produce a backchannel • To elicit a backchannel from the user, if desired: Include as many cues as possible in the system’s final IPU. Agustín Gravano Interspeech 2009 15
Summary • Study of backchannel-inviting cues. • Objective, automatically computable. • Combined cues. • Improve turn-taking decisions of IVR systems. • Results drawn from task-oriented dialogues. • Not necessarily generalizable. • Suitable for most IVR domains. • SIGdial 2009: Study of turn-yielding cues. Agustín Gravano Interspeech 2009 16
Special thanks to… • My advisor, Julia Hirschberg • Thesis Committee Members • Maxine Eskenazi, Kathy Mc. Keown, Becky Passonneau, Amanda Stent. • Speech Lab at Columbia University • Stefan Benus, Fadi Biadsy, Sasha Caskey, Bob Coyne, Frank Enos, Martin Jansche, Jackson Liscombe, Sameer Maskey, Andrew Rosenberg. • Collaborators • Gregory Ward and Elisa Sneed German (Northwestern U); Ani Nenkova (UPenn); Héctor Chávez, David Elson, Michel Galley, Enrique Henestroza, Hanae Koiso, Shira Mitchell, Michael Mulley, Kristen Parton, Ilia Vovsha, Lauren Wilcox. Agustín Gravano Interspeech 2009 17
- Slides: 17