Automatic transcription of courtroom speech

In this paper we describe our on-going effort in developing a speech recognition system for transcribing courtroom hearings. Court hearings are a rich source of naturally occurring speech data, much of which is in public domain. The presence of multiple microphones coupled with presence of noise and reverberation makes the problem simultaneously rich and challenging. We have exploited the availability of multiple channels to mitigate, to some extent, the noise problem prevalent in courtroom speech. By using a novel technique for channel change detection, domain-specific language modeling, and unsupervised channel adaptation we have been able to achieve a word error rate (WER) of 36% on actual courtroom hearings. We also report on acoustic modeling experiments using “legal” transcripts for 120 hours of court hearings in a lightly supervised mode.