2. 1 Spoken Dialogue Systems Error Detection and Correction in Spoken Dialogue Systems

3. 2 Spoken Dialogue Systems Outline Avoiding errors Detecting errors From the user side: what cues does the user provide to indicate an error? From the system side: how likely is it the system made an error? Dealing with Errors: what can the system do when it thinks an error has occurred? Evaluating SDS: evaluating ‘problem’ dialogues

4. 3 Spoken Dialogue Systems Avoiding misunderstandings The problem By imitating human performance Timing and grounding (Clark ’03)Clark ’03 Confirmation strategies Clarification and repair subdialogues

5. 4 Spoken Dialogue Systems Outline Avoiding errors Detecting errors From the user side: what cues does the user provide to indicate an error? From the system side: how likely is it the system made an error? Dealing with Errors: what can the system do when it thinks an error has occurred? Evaluating SDS: evaluating ‘problem’ dialogues

6. 5 Spoken Dialogue Systems Learning from Human Behavior: Features in repetition corrections(KTH) 0 10 20 30 40 50 more clearly articulated increased loudness shifting of focus Percentage of all repetitions adults children

7. 6 Spoken Dialogue Systems Learning from Human Behavior (Krahmer et al ’01) Learning from human behavior ‘go on’ and ‘go back’ signals in grounding situations (implicit/explicit verification) Positive: short turns, unmarked word order, confirmation, answers, no corrections or repetitions, new info Negative: long turns, marked word order, disconfirmation, no answer, corrections, repetitions, no new info

8. 7 Spoken Dialogue Systems Hypotheses supported but… –Can these cues be identified automatically? –How might they affect the design of SDS?

9. 8 Spoken Dialogue Systems Outline Avoiding errors Detecting errors From the user side: what cues does the user provide to indicate an error? From the system side: how likely is it the system made an error? Dealing with Errors: what can the system do when it thinks an error has occurred? Evaluating SDS: evaluating ‘problem’ dialogues

10. 9 Spoken Dialogue Systems Systems Have Trouble Knowing When They’ve Made a Mistake Hard for humans to correct system misconceptions (Krahmer et al `99) User: I want to go to Boston. System: What day do you want to go to Baltimore? Easier: answering explicit requests for confirmation or responding to ASR rejections System: Did you say you want to go to Baltimore? System: I'm sorry. I didn't understand you. Could you please repeat your utterance?

11. 10 Spoken Dialogue Systems But constant confirmation or over-cautious rejection lengthens dialogue and decreases user satisfaction

12. 11 Spoken Dialogue Systems …And Systems Have Trouble Recognizing User Corrections Probability of recognition failures increases after a misrecognition (Levow ‘98) Corrections of system errors often hyperarticulated (louder, slower, more internal pauses, exaggerated pronunciation)  more ASR error (Wade et al ‘92, Oviatt et al ‘96, Swerts & Ostendorf ‘97, Levow ‘98, Bell & Gustafson ‘99)

13. 12 Spoken Dialogue Systems Can Prosodic Information Help Systems Perform Better? If errors occur where speaker turns are prosodically ‘marked’…. Can we recognize turns that will be misrecognized by examining their prosody? Can we modify our dialogue and recognition strategies to handle corrections more appropriately?

14. 13 Spoken Dialogue Systems Approach Collect corpus from interactive voice response system Identify speaker ‘turns’ –incorrectly recognized –where speakers first aware of error –that correct misrecognitions Identify prosodic features of turns in each category and compare to other turns Use Machine Learning techniques to train a classifier to make these distinctions automatically misrecognition correction aware site

15. 14 Spoken Dialogue Systems Turn Types TOOT: Hi. This is AT&T Amtrak Schedule System. This is TOOT. How may I help you? User: Hello. I would like trains from Philadelphia to New York leaving on Sunday at ten thirty in the evening. TOOT: Which city do you want to go to? User: New York. misrecognition correction aware site

16. 15 Spoken Dialogue Systems TOOT Dialogues Collected to study effects of differences in dialogue strategy on user performance and satisfaction (Litman & Pan ‘99) type of initiative (system, user, mixed) type of confirmation (explicit, implicit, none) adaptability condition Subjects 39 summer students 16/23 (F/M) 20/19 (native speaker/non)

17. 16 Spoken Dialogue Systems Platform: combined over-the-phone ASR and TTS (Kamm et al ‘97) with web access to train information Task: find train information for 4 scenarios Corpus for current study:  2328 speaker turns, 52 dialogues Misrecognitions  Overall word accuracy: 61%  Overall concept accuracy(CA): 71%  “I want to go to Boston from Philadelphia” (2 domain concepts)  recognized as “I want to go to Boston” (one concept) = 50%

18. 17 Spoken Dialogue Systems A Successful Dialogue S: Hi, this is AT&T Amtrak schedule system. This is TOOT. How may I help you? U: I would like a train to New York City from Philadelphia on Sunday at ten thirty P M S: I heard you say “go to New York City from Philadelphia on Sunday approximately at ten thirty p.m." Do you want me to find the trains from Philadelphia to New York City on Sunday approximately at ten thirty p. m. now? U: Yes. S: I am going to get the train schedule for you....

19. 18 Spoken Dialogue Systems Do Misrecognitions, Awares, and Corrections Differ from Other Turns? For each type of turn: For each speaker, for each prosodic feature, calculate mean values for e.g. all correctly recognized speaker turns and for all incorrectly recognized turns Perform paired t-tests on these speaker pairs of means (e.g., for each speaker, pairing mean values for correctly and incorrectly recognized turns)

20. 19 Spoken Dialogue Systems How: Prosodic Features Examined per Turn Raw prosodic/acoustic features f0 maximum and mean (pitch excursion/range) rms maximum and mean (amplitude) total duration duration of preceding silence amount of silence within turn speaking rate (estimated from syllables of recognized string per second) Normalized versions of each feature (compared to first turn in task, to previous turn in task, Z scores)

21. 20 Spoken Dialogue Systems Distinguishing Correct Recognitions from Misrecognitions (NAACL ‘00) Misrecognitions differ prosodically from correct recognitions in F0 maximum (higher) RMS maximum (louder) turn duration (longer) preceding pause (longer) slower Effect holds up across speakers and even when hyperarticulated turns are excluded

22. 21 Spoken Dialogue Systems WER-Based Results Misrecognitions are higher in pitch, louder, longer, more preceding pause and less internal silence

23. 22 Spoken Dialogue Systems Predicting Turn Types Automatically Ripper (Cohen ‘96) automatically induces rule sets for predicting turn types greedy search guided by measure of information gain input: vectors of feature values output: ordered rules for predicting dependent variable and (X-validated) scores for each rule set Independent variables: all prosodic features, raw and normalized experimental conditions (adaptability of system, initiative type, confirmation style, subject, task) gender, native/non-native status ASR recognized string, grammar, and acoustic confidence score

24. 23 Spoken Dialogue Systems ML Results: WER-defined Misrecognition

25. 24 Spoken Dialogue Systems Best Rule-Set for Predicting WER if (conf = 1.27) ^ then F if (conf <= -4.34) then F if (tempo <=.81) then F If (conf <= -4.09 then F If (conf <= -2.46 ^ str contains “help” then F If conf =.77 ^ tempo <=.25 then F If str contains “nope” then F If dur >= 1.71 ^ tempo <= 1.76 then F else T Using prosody, ASR conf, ASR string, ASR grammar

26. 25 Spoken Dialogue Systems Outline Avoiding errors Detecting errors From the user side: what cues does the user provide to indicate an error? From the system side: how likely is it the system made an error? Dealing with Errors: what can the system do when it thinks an error has occurred? Evaluating SDS: evaluating ‘problem’ dialogues

27. 26 Spoken Dialogue Systems Error Handling Strategies If systems can recognize their lack of recognition, how should they inform the user that they don’t understand (Goldberg et al ’03)? System rephrasing vs. repetitions vs. statement of not understanding Apologies What behaviors might these produce? Hyperarticulation User frustration User repetition vs. rephrasing

28. 27 Spoken Dialogue Systems What lessons do we learn? When users are frustrated they are generally harder to recognize accurately When users are increasingly misrecognized they tend to be misrecognized more often and become increasingly frustrated Apologies combined with rephrasing of system prompts tend to decrease frustration and improve WER: Don’t just repeat! Users are better recognized when they rephrase their input

29. 28 Spoken Dialogue Systems How does an SDS Recognize a Correction? (ICSLP ’00) TOOT: Hi. This is AT&T Amtrak Schedule System. This is TOOT. How may I help you? User: Hello. I would like trains from Philadelphia to New York leaving on Sunday at ten thirty in the evening. TOOT: Which city do you want to go to? User: New York. correction

30. 29 Spoken Dialogue Systems Serious Problem for Spoken Dialogue Systems 29% of turns in our corpus are corrections 52% of corrections are hyperarticulated but only 12% of other turns Corrections are misrecognized at least twice as often as non-corrections (60% vs. 31%) But corrections are no more likely to be rejected than non-corrections…. (9% vs. 8%) Are corrections also measurably distinct from non- corrections?

31. 30 Spoken Dialogue Systems Prosodic Indicators of Corrections Corrections differ from other turns prosodically: longer, louder, higher in pitch excursion, longer preceding pause, less internal silence ML results: Baseline: 30% error norm’d prosody +non-prosody: 18.45% +/- 0.78% automatic: 21.48% +/- 0.68%

32. 31 Spoken Dialogue Systems Prosodic Indicators of Corrections Corrections differ from other turns prosodically: longer, louder, higher in pitch excursion, longer preceding pause, less internal silence

33. 32 Spoken Dialogue Systems ML Rules for Correction Prediction Baseline: 30% error (predict not correction) norm’d prosody +non-prosody: 18.45% +/- 0.78% automatic: 21.48% +/- 0.68% TRUE :- gram=universal, f0max>=0.96, dur>=6.55 TRUE :- gram=universal, zeros>=0.57, asr<=-2.95 TRUE :- gram=universal, f0max =1.21, zeros>=0.71 TRUE :- dur>=0.76, asr<=-2.97, strat=UsrNoConf TRUE :- dur>=2.28, ppau<=0.86 TRUE :- rmsav>=1.11, strat=MixedImplicit, gram=cityname, f0max>=0.70 default FALSE

34. 33 Spoken Dialogue Systems Corrections in Context Similar in prosodic features but… What about their form and content? How do system behaviors affect the corrections users produce? What sort of corrections are most, least effective? When users correct the same mistake more than once, do they vary their strategy in productive ways?

35. 34 Spoken Dialogue Systems User Correction Behavior Correction classes: ‘omits’ and ‘repetitions’ lead to fewer misrecognitions than ‘adds’ and ‘paraphrases’ Turns that correct rejections are more likely to be repetitions, while turns correcting misrecognitions are more likely to be omits

36. 35 Spoken Dialogue Systems Type of correction sensitive to strategy much more likely to exactly repeat their misrecognized utterance in a system-initiative environment much more likely to correct by omitting information if no system confirmation than with explicit confirmation omits used more in MixedImplicit and UserNoConfirm conditions “Restarts” unlikely to be recognized (77% misrecognized) and skewed in distribution: 31% of corrections are “restarts” in MI and UNC

37. 36 Spoken Dialogue Systems None for SE, where initial turns well recognized It doesn’t pay to start over!

38. 37 Spoken Dialogue Systems Outline Avoiding errors Detecting errors From the user side: what cues does the user provide to indicate an error? From the system side: how likely is it the system made an error? Dealing with Errors: what can the system do when it thinks an error has occurred? Evaluating SDS: evaluating ‘problem’ dialogues

39. 38 Spoken Dialogue Systems Recognizing `Problematic’ Dialogues Hastie et alHastie et al, “What’s the Trouble?” ACL 2002 How to define a dialogue as problematic? User satisfaction is low Task is not completed How to recognize? Train on a corpus of recorded dialogues (1242 DARPA Communicator dialogues) Predict –User Satisfaction –Task Completion (0,1,2)

40. 39 Spoken Dialogue Systems

41. 40 Spoken Dialogue Systems Results