Correcting speech recognition errors on a mobile touchscreen
device is an unavoidable but time-consuming task that re-
quires a lot of user effort. To reduce this user effort, we
previously proposed an error correction method using long
context match with Web N-gram, which we combined with
a simple gesture-based user interface. This method automat-
ically replaces an error word with its corresponding correct
word. However, it was evaluated only substitution errors in
sentences, each of which involves only one error. In this pa-
per, we extend this method to be used for more general cases
when a sentence has more than one error. It recovers not only
substitution errors but also deletion errors and insertion er-
rors. For recovering deletion errors, it predicts a deleted word
based on the phonemes and the part-of-speech tags of its sur-
rounding words. Our experimental results show that the pro-
posed method recovered the errors more accurately with less
user effort than the conventional Word Confusion Network
based error correction interface.
各種検索
サポート
ヘルプ