1 / 51

Error Correction Spiral

Characterizing and Recognizing Spoken Corrections in Human-Computer Dialog Gina-Anne Levow August 25, 1998. Error Correction Spiral. U: Give me the price for AT&T. S: Hewlett-Packard was 83 ¾, up 2 ½ since yesterday. U: Give me the price for AT&T. S: Data General was at 10 ½ up a quarter.

abie
Download Presentation

Error Correction Spiral

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Characterizing and RecognizingSpoken Corrections inHuman-Computer DialogGina-Anne LevowAugust 25, 1998

  2. Error Correction Spiral • U: Give me the price for AT&T. • S: Hewlett-Packard was 83 ¾, up 2 ½ since yesterday. • U: Give me the price for AT&T. • S: Data General was at 10 ½ up a quarter. • U: Give me the price for AT&T. • S: Hewlett-Packard was 83 ¾, up 2 ½. • U: Give me the price for American Telephone and Telegraph. • S: Excuse me?

  3. Identifying Corrections • Most "Reasoning" Approaches • Correction => Violates Task, Belief Constraint • Requires Tight Task, Belief Model • Often Requires Accurate Recognition • This Approach • Uses Acoustic or Lexical Information • Content, Context Independent

  4. Accomplishments • Corrections vs Original Inputs • Significant Differences: Duration, Pause, Pitch • Corrections vs Recognizer Models • Contrasts: Phonology and Duration • Correction Recognition • Decision Tree Classifier: 65-77% accuracy • Human Baseline ~80%

  5. Why Corrections? • Recognizer Error Rates ~25% • REAL meaning of utterance • user intent • Corrections misrecognized 2.5X as often • Hard to Correct => Poor Quality System

  6. Why it's Necessary • Error Repair Requires Detection • Errors can be very difficult to detect • E.g. Misrecognitions • Focus Repair Efforts • Corrections Decrease Recognition Accuracy • Adaptation Requires Identification

  7. Why is it Hard? • Recognition Failures and Errors • Repetition <> Correction • 500 Strings => 6700 Instances (80%) • Speech Recognition Technology • Variation - Undesirable, Suppressed

  8. Corrections Within

  9. Roadmap • Data Collection and Description • SpeechActs System & Field Trial • Characterizing Corrections • Original-Repeat Pair Data Analysis • Acoustic and Phonological Measures & Results • Recognizing Corrections • Conclusions and Future Work

  10. SpeechActs System • Speech-Only System over the Telephone • Access to Common Desktop Applications • Email, Calendar, Weather, Stock Quotes • BBN's Hark Speech Recognition, Centigram TruVoice Speech Synthesis • In-house: Natural Language Analysis Back-end Applications, Dialog Manager

  11. Example Interaction • SpeechActs: You have 14 new messages and 47 old messages. The first new message is from Eric Baatz regarding "report completed". • User: Let me hear it. • SpeechActs: "The first draft is ready for your comments." • User: Reply and Include the current message. • SpeechActs: Preparing message to Eric Baatz. Begin recording after the tone. When finished, pause for several seconds. • User: Eric, I'll get those to you this afternoon. • SpeechActs: Say cancel, send or review.

  12. Example Interaction: Con't • User: Send. • SpeechActs: Message Sent. What now? • User: Next message. • SpeechActs: New Message two from Stuart Adams, subject "Can we meet at 3:00 today?" • User: Switch to Calendar.

  13. System Data Overview • Approximately 60 hours of interactions • Digitized at 8kHz, 8-bit mu-law encoding • 18 subjects: 14 novices, 4 experts, single shots • 7529 user utterances, 1961 errors ~25% error • P(error | correct) = 18%; P(error | error) = 44%

  14. System: Recognition Error Types • Rejection Errors - Below Recognition Level • U: Switch to Weather • S (Heard): <nothing> • S (said): Huh? • Misrecognition Errors - Substitution in Text • U: Switch to Weather • S (Heard): Switch to Calendar • S (Said): On Tuesday August 25, you have defense • 1250 Rejections ~2/3 • 706 Misrecognitions ~1/3

  15. Roadmap • Data Collection and Description • SpeechActs System & Field Trial • Characterizing Corrections • Original-Repeat Pair Data Analysis • Acoustic and Phonological Measures & Results • Divergence from Recognizer Models • Recognizing Corrections • Conclusions and Future Work

  16. Analysis: Data • 300 Original Input-Repeat Correction Pairs • Lexically Matched, Same Speaker • Example: • S: (Said): Please say mail, calendar, weather. • U: Switch to Weather. Original • S (Said): Huh? • U: Switch to Weather. Repeat.

  17. Analysis: Duration • Automatic Forced Alignment, Hand-Edited • Total: Speech Onset to End of Utterance • Speech: Total - Internal Silence • Contrasts: Original Input/Repeat Correction • Total: Increases 12.5% on average • Speech: Increases 9% on average

  18. Analysis: Pause • Utterance Internal Silence > 10ms • Not Preceding Unvoiced Stops(t), Affricates(ch) • Contrasts: Original Input/Repeat Correction • Absolute: 46% Increase • Ratio of Silence to Total Duration: 58% Increase

  19. Pitch Tracks

  20. Analysis: Pitch I • ESPS/Waves+ Pitch Tracker, Hand-Edited • Normalized Per-Subject: • (Value-Subject Mean) / (Subject Std Dev) • Pitch Maximum, Minimum, Range • Whole Utterance & Last Word • Contrasts: Original Input/Repeat Correction • Significant Decrease in Pitch Minimum • Whole Utterance & Last Word

  21. Analysis: Pitch II

  22. Analysis: Pitch III • Internal Pitch Contours: Pitch Accent • Steepest Rise, Steepest Fall, Slope Sum • Overall => Not Significant • Misrecognitions Only: Original vs Repeat • Significant Increases: Steepest Rise, Slope Sum

  23. Pitch Contour Detail • Exclude Boundary Tone Region • 5-Point median smoothing (Taylor 1996) • Piecewise linear contour between max and min

  24. Analysis: Overview • Significant Differences: Original/Correction • Duration & Pause • Significant Increases: Original vs Correction • Pitch • Significant Decrease in Pitch Minimum • Increase in Final Falling Contours • Misrecognitions: Increase in Pitch Variability • Conversational-to-Clear Speech Shift • Contrastive Use of Pitch Accent

  25. Roadmap • Data Collection and Description • SpeechActs System & Field Trial • Characterizing Corrections • Original-Repeat Pair Data Analysis • Acoustic and Phonological Measures & Results • Divergence from Recognizer Models • Recognizing Corrections • Conclusions and Future Work

  26. Analysis: Phonology • Reduced Form => Citation Form • Schwa to unreduced vowel (~20) • E.g. Switch t' mail => Switch to mail. • Unreleased or Flapped 't' => Released 't' (~50) • E.g. Read message tweny => Read message twenty • Citation Form => Hyperclear Form • Vowel or Syllabic Insertion (~20) • E.g. Goodbye => Goodba-aye

  27. Analysis: Overview II • Original vs Correction & Recognizer Model • Phonology • Reduced Form => Citation Form => Hyperclear Form • Conversational to (Hyper) Clear Shift • Duration • Contrast between Final and Non-final Words • Departure from ASR Model • Increase for Corrections, especially Final Words

  28. Roadmap • Data Collection and Description • SpeechActs System & Field Trial • Characterizing Corrections • Original-Repeat Pair Data Analysis • Acoustic and Phonological Measures & Results • Divergence from Recognizer Models • Recognizing Corrections • Conclusions and Future Work

  29. Learning Method Options • (K)-Nearest Neighbor • Need Commensurable Attribute Values • Sensitive to Irrelevant Attributes • Labeling Speed - Training Set Size • Neural Nets • Hard to Interpret • Can Require More Computation & Training Data • +Fast, Accurate when Trained • Decision Trees • Intelligible, Robust to Irrelevant Attributes • +Fast, Compact when Trained • ?Rectangular Decision Boundaries, Don't Test Feature Combinations • Alternative: Mixture of Experts

  30. Learning Method Options • (K)-Nearest Neighbor • Need Commensurable Attribute Values • Sensitive to Irrelevant Attributes • Labeling Speed - Training Set Size • Neural Nets • Hard to Interpret • Can Require More Computation & Training Data • +Fast, Accurate when Trained • Decision Trees <= • Intelligible, Robust to Irrelevant Attributes • +Fast, Compact when Trained • ?Rectangular Decision Boundaries, Don't Test Feature Combinations

  31. Amplitude Max, Mean, Last Max-Last (ampdiff) Mean-Last (ampdelta) Pitch Max, Min, Range Global, Last Word Range/Total Contour Max, min, sum slope Decision Tree Features • 38 Features Total, E.g. • 15 for best trees • Pause • Total Pause Duration • Pause / Total Duration • Duration • Total Duration (uttdur) • Speaking Rate (sps) • Normalized Duration

  32. Decision Tree Training & Testing • Data: 50% Original Inputs, 50% Repeat Corrections • Classifier Labels: Original, Correction • 7-Way Cross-Validation • Train on 6/7 of data, Test on remaining 1/7 • Subsets drawn at random according to distribution • Cycle through all subsets, training & testing • Report average results on unseen test data

  33. Recognizer: Results (Overall) • Tree Size: 57 (unpruned), 37 (pruned) • Minimum of 10 nodes per branch required • First Split: Normalized Duration (All Trees) • Most Important Features: • Normalized & Absolute Duration, Speaking Rate • 65% Accuracy - Null Baseline-50%

  34. Example Tree

  35. Classifier Results: Misrecognitions • Most important features: • Absolute and Normalized Duration • Pitch Minimum and Pitch Slope • 77% accuracy (with text) • 65% (acoustic features only) • Null baseline - 50% • Human baseline - 79.4% (Hauptman & Rudnicky 1990)

  36. Classifier Results: Misrecognitions • Most important features: • Absolute and Normalized Duration • Pitch Minimum and Pitch Slope • 77% accuracy (with text) • 65% (acoustic features only) • Errors, most trees: ½ false positive, ½ false negative • Null baseline - 50% • Human baseline - 79.4% (Hauptman & Rudnicky 1990)

  37. Misrecognition Classifier

  38. Roadmap • Data Collection and Description • Characterizing Corrections • Recognizing Corrections • Conclusions and Future Work

  39. Accomplishments • Contrasts between Originals vs Corrections • Significant Differences in Duration, Pause, Pitch • Conversational-to-Clear Speech Shifts • Shifts away from Recognizer Models • Corrections Recognized at 65-77% • Near-human Levels

  40. The Recipe • Original/Correction Training Set (300+ sets) • Labeled, Transcribed, Digitized, Corpus or Wizard • Acoustic Analyses • Pitch Tracking, Silence Detection, Speaking Rate,... • Classifier Training & Tuning • Confidence Measure (Weighted Pessimistic Error) • Phonological Rule Extraction • Durational Contrast Modeling • Repair Dialog Management

  41. Future Work • Modify ASR Duration Model for Correction • Reflect Phonological and Duration Change • Identify Locus of Correction for Misrecognitions • Preliminary tests: • 26/28 Corrected Words Detected, 2 False Alarms

More Related