Matching Inconsistently Spelled Names in Automatic Speech Recognizer Output for Information Retrieval

Many proper names are spelled inconsistently in speech recognizer output, posing a problem for applications where locating mentions of named entities is critical. We model the distortion in the spelling of a name due to the speech recognizer as the effect of a noisy channel. The models follow the framework of the IBM translation models. The model is trained using a parallel text of closed caption and automatic speech recognition output. We also test a string edit distance based method. The effectiveness of these models is evaluated on a name query retrieval task. Our methods result in a 60% improvement in F1. We also demonstrate why the problem has not been critical in TREC and TDT tasks.