Tarniceriu, Adrian DanRimoldi, BixioDillenbourg, Pierre2013-10-072013-10-072013-10-07201310.1109/SpeD.2013.6682648https://infoscience.epfl.ch/handle/20.500.14299/96132WOS:000330672700005As different text input devices lead to different typing error patterns, considering the device characteristics when designing an error correction mechanism can lead to significantly improved results. In this paper, we propose and evaluate a spelling algorithm specifically designed for a five-key chording keyboard. It is based on the maximum a posteriori probability criterion, taking into account a dictionary model and the probabilities that one character is typed for another. These probabilities are determined experimentally. In our experiment, the proposed method reduced the substitution error rate from 7.60% to 1.59%. As comparison, MsWord and iSpell reduced the substitution error rates to 3.12% and 3.94%, respectively.error correctionconfusion matrixmaximum a posteriori probabilitychording keyboardtext::conference output::conference proceedings::conference paper