Spoken Correction for Chinese Text Entry

  • Bo-June Paul Hsu
  • James Glass
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4274)


With an average of 17 Chinese characters per phonetic syllable, correcting conversion errors with current phonetic input method editors (IMEs) is often painstaking and time consuming. We explore the application of spoken character description as a correction interface for Chinese text entry, in part motivated by the common practice of describing Chinese characters in names for self-introductions. In this work, we analyze typical character descriptions, extend a commercial IME with a spoken correction interface, and evaluate the resulting system in a user study. Preliminary results suggest that although correcting IME conversion errors with spoken character descriptions may not be more effective than traditional techniques for everyone, nearly all users see the potential benefit of such a system and would recommend it to friends.


User Study Chinese Character Candidate List Target Character Description Type 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Miniwatts Marketing Group: Internet users by languages. Internet World Statistics Website (March 31, 2006),
  2. 2.
    iResearch Inc.: The Number of IM Users Will Reach 200 million by 2010 in China. iResearch–China Internet Research Center Website (May 17, 2006),
  3. 3.
    Xinhua News Agency: Chinese bloggers to reach 100 million in 2007. China View Website (May 6, 2006),
  4. 4.
    Gao, J., Goodman, J., Li, M., Lee, K.: Toward a Unified Approach to Statistical Language Modeling for Chinese. ACM Transactions on Asian Language Information Processing 1(1), 3–33 (2002)CrossRefGoogle Scholar
  5. 5.
    Hsu, W., Chen, Y.: On Phoneme-To-Character Conversion Systems in Chinese Processing. Journal of Chinese Institute of Engineers 5, 573–579 (1999)CrossRefGoogle Scholar
  6. 6.
    Tsai, J., Chiang, T., Hsu, W.: Applying Meaningful Word-Pair Identifier to the Chinese Syllable-to-Word Conversion Problem. In: Proc. ROCLING (2004)Google Scholar
  7. 7.
    Microsoft Corp.: 微軟新注音輸入法 2003. Microsoft Website (June 15, 2006),
  8. 8.
    IQ Technology Inc.: Natural Chinese Input 8. IQ Technology Website (June 15, 2006),
  9. 9.
    Tsai, C., Wang, N., Huang, P., Shen, J.: Open Vocabulary Chinese Name Recognition with the Help of Character Description and Syllable Spelling Recognition. In: Proc. ICASSP (2005)Google Scholar
  10. 10.
    CNS11643 國家中文標準交換碼. CNS11643 中文全字庫Website (JunE 15, 2006),
  11. 11.
    Graff, D., Chen, K.: Chinese Gigaword. In: Linguistic Data Consortium (2003)Google Scholar
  12. 12.
    Tsai, C.: Common Chinese Names. Chih-Hao Tsai’s Technology Page Website (December 5, 2005),
  13. 13.
    Microsoft Corp.: SAPI 5.1. Microsoft Website (March 3, 2003),
  14. 14.
    Microsoft Corp.: Install and Train Speech Recognition. Microsoft Office Online Website (June 15, 2006),
  15. 15.
    Peterson, E.: CEDICT: Chinese-English Dictionary. On-line Chinese Tools Website (June 15, 2006),
  16. 16.
    Institute of Linguistics, Academia Sinica: 漢字構形資料庫. 中研院資訊所 Website (August 15, 2005)
  17. 17.

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Bo-June Paul Hsu
    • 1
  • James Glass
    • 1
  1. 1.MIT Computer Science and Artificial Intelligence LaboratoryCambridgeUSA

Personalised recommendations