1 / 31

Error Correction of Continuous Handwriting Recognition by Multimodal Fusion

Error Correction of Continuous Handwriting Recognition by Multimodal Fusion. Xiang Ao 11/4/2014. Error correction by speech. Why error correction matters?. Correction of recognition errors is important for a recognition-based interfaces, because Recognition errors are inevitable.

jerry-dale
Télécharger la présentation

Error Correction of Continuous Handwriting Recognition by Multimodal Fusion

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. Error Correction of Continuous Handwriting Recognition by Multimodal Fusion Xiang Ao 11/4/2014

  2. Error correction by speech

  3. Why error correction matters? • Correction of recognition errors is important for a recognition-based interfaces, because • Recognition errors are inevitable. • Usually, these errors needs correction. • User satisfaction is not only determined by recognition accuracy, but also by • the complexity of error correction dialogues • the amount gained for the effort of correction.

  4. Our approach Existing Correction Techniques • Respeaking • N-best List • Adaptive modalities • Mutimodal correction

  5. Why speech? • We use speech to correct handwriting recognition errors because: • It is natural • It mimics our habit of proofreading. • It is efficient • It needs little effort • It does not make busy hands busier. • It is effective • Complimentarity and redundancy of different modalities • cross-modal dependency

  6. Find the handwriting recognition result whose pronunciation best matches the speech.

  7. The fusion algorithm

  8. The fusion • Task: Find the handwriting recognition result whose pronunciation best matches the speech.

  9. The fusion – the keywords • Find the handwriting recognition result whose pronunciation best matches the speech. • “handwriting recognition result” • What is the search space? • “matches” • “Matching” implies “comparing”. How is the “comparing”? • “Find” • How to make the searching efficient?

  10. is recognized as “棍”. However, it is “概” segmented as should be Handwriting recognition errors and candidates • Handwriting recognition errors • Character recognition errors • Character segmentation (extraction) errors

  11. 概 椒 橄 k candidates M Handwriting recognition errors and candidates • Handwriting recognition candidates • Character recognition candidates

  12. Over-segmentation fragment Handwriting recognition errors and candidates • Handwriting recognition candidates • Character segmentation candidates Six graphemic pattern

  13. The number of paths: Handwriting recognition errors and candidates Fragment graph

  14. Handwriting recognition errors and candidates For a text line with T fragments, the number of recognition candidates is:

  15. The fusion – the keywords • Find the handwriting recognition result whose pronunciation best matches the speech. • “handwriting recognition result” • What is the search space? • “matches” • “Matching” implies “comparing”. How is the “comparing”? • “Find” • How to make the searching efficient?

  16. Phoneme • Hanyu pinyin is used as a symbolized pronunciation of a word. • A pinyin is composed of an initial, a final and a tone. • A phoneme is defined as a pair: [initial, final] Initial: t 逃 táo Phoneme: [t, ao] Finla: ao

  17. Phonemic similarity

  18. The fusion – phoneme sequences’ similarity • A phoneme sequence is written as • Similarity of two phoneme sequence is defined as their Levenshtein distance (Edit distance). kitten → sitten (substitution of 's' for 'k') sitten → sittin (substitution of 'i' for 'e') sittin → sitting (insert 'g' at the end)

  19. The fusion – the keywords • Find the handwriting recognition result whose pronunciation best matches the speech. • “handwriting recognition result” • What is the search space? • “matches” • “Matching” implies “comparing”. How is the “comparing”? • “Find” • How to make the searching efficient?

  20. Fusion by an Exhaustive Search S1, S2, S3, S4, S5, S6, S7, S8, S9, S10, S11,… Compare Speech:

  21. Fusion by an Exhaustive Search • The time complexity of the exhaustive search:

  22. Fusion by a Divide-Conquer Search Over-segmentation Speech:

  23. [0,3],[4,7] [0,2],[3,7] [0,1],[2,7] [0,4],[5,7] [0,5],[6,7] q Fusion by a Divide-Conquer Search

  24. Fusion by a Divide-Conquer Search • The time complexity of the divide-conquer search:

  25. Weighted Phoneme • Speech recognition has errors, which make its phonemes inaccurate. • Candidates of speech recognition could improve the phoneme representation of speech. • Weighted Phoneme

  26. “逃” Weighted Phoneme

  27. Null phonemes Weighted Phoneme • Weighted phonemes can also represent different segmentations in speech recognition

  28. Weighted Phoneme • Similarity of weighted phonemes

  29. Demo

  30. The fusion - summary • Find the handwriting recognition result whose pronunciation best matches the speech. • “handwriting recognition result” • Candidates of segmentation and recogntion. • “matches” • Phoneme • Weighted phoneme • Similarity of (weighted) phoneme sequences • “Find” • A divide-conqure search

  31. Thanks!

More Related