Recognizing Call-center Speech Using Models Trained from Other Domains

In this paper, we introduce a new conversational speech task – recognizing call-center speech – using data collected from Dragon’s own technical support line. We compare performance of models trained from conversational telephone speech (the Switchboard corpus) and models trained from predominantly read, microphone speech, and report on a series of experiments focusing on adapting the microphone speech models to the telephone channel and conversational task. We also discuss the importance of task-specific language model data. We benchmark our test set by comparing the performance of our 1998 Switchboard Evaluation system to that of our simpler call-center system.