Robust speech recognition using noise suppression based on multiple composite models and multi-pass search

摘要

This paper presents robust speech recognition using a noise suppression method based on multi-model compositions and multi-pass search. In real environments, many kinds of noise signals exists, and input speech for speech recognition systems include them. Our task in the E-Nightingale project is speech recognition of voice memoranda spoken by nurses during actual work at hospitals. To obtain good recognized candidates, suppressing many kinds of noise signals at once to find target speech is important. First, before noise suppression, to find speech and noise label sequences, we introduce multi-pass search with acoustic models including many kinds of noise models and their compositions, their n-gram models, and their lexicon. Second, noise suppression based on models is performed using the multiple composite models selected by recognized label sequences with time alignments. We evaluated this approach using the E-Nightingale task, and the proposed method outperformed the conventional method.