We propose an efficient error correction method and a simple
gesture-based interface for speech recognition, where users mark
the error region once, and then the word will be replaced by another
candidate. Assuming that the words preceding/succeeding the error
region are validated by the user, we search the Web n-grams for
long word sequences matched to such a context. The acoustic
features of the error region are also utilized to rerank the candidate
words. The experimental result using CSJ proved the effectiveness
of our method. 30.2% of the error words were corrected by a single
operation.
各種検索
サポート
ヘルプ