ABSTRACT
A comparison of the accuracy of comprehension of Instant Messaging (IM) messages composed using a keyboard, handwriting recognition and speech recognition was performed. The participants in the study were shown text messages either containing no errors or having errors caused by typing, handwriting or speech recognition. They demonstrated their understanding of the messages by correcting the errors as they retyped the messages. The time to correct typographical errors was not significantly different from the time to type messages without errors. Speech and handwriting recognition errors in the text took significantly longer to correct than typographical errors, and the results were significantly less accurate. Interestingly, participants expressed slightly higher confidence in their understanding of messages containing speech recognition errors than handwriting, but the accuracy results from those two categories were not significantly different.
- Baron, N.S. Instant Messaging and the Future of Language. CACM, 48(7), (2005), 29 -- 31. Google ScholarDigital Library
- Campbell, J.D., Stanziola, E. and Feng, J., Instant Messaging: Between the Messages. In Proc IEEE Systems, Man and Cybernetics Conference, IEEE Press, (2003), 2193 -- 2198.Google ScholarCross Ref
- Isaacs, E., Walendowski, A., Whittaker, S., Schiano, D.J. and Kamm, C., The Character, Functions, and Styles of Instant Messaging in the Workplace. In Proc CSCW 2002, ACM Press, (2002), 11--20. Google ScholarDigital Library
- Suhm, B., Myers, B.A. and Waibel, A., Model-Based and Empirical Evaluation of Multimodal Interactive Error Correction. In Proc CHI 99, ACM Press, (1999), 584 -- 591. Google ScholarDigital Library
Index Terms
- Instant messaging comprehension with non-keyboard composition
Recommendations
Indic script family and its offline handwriting recognition for characters/digits and words: a comprehensive survey
AbstractHandwriting recognition has become an active area of research in pattern recognition and machine learning in recent years. Handwriting recognition systems have a variety of applications ranging from digital character conversion to signboard ...
Audio-video based character recognition for handwritten mathematical content in classroom videos
Recognizing handwritten equations is a challenging problem, and even more so when they are written in a classroom environment. However, since videos of the handwritten text and the accompanying audio refer to the same content, a combination of video and ...
Word graph based speech rcognition error correction by handwriting input
ICMI '06: Proceedings of the 8th international conference on Multimodal interfacesWe propose a convenient handwriting user interface for correcting speech recognition errors efficiently. Via the proposed hand-marked correction on the displayed recognition result, substitution, deletion and insertion errors can be corrected ...
Comments