Paper: Matching Inconsistently Spelled Names In Automatic Speech Recognizer Output For Information Retrieval

ACL ID H05-1057
Title Matching Inconsistently Spelled Names In Automatic Speech Recognizer Output For Information Retrieval
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors

Many proper names are spelled inconsis- tently 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 fol- low the framework of the IBM translation models. The model is trained using a par- allel text of closed caption and automatic speech recognition output. We also test a string edit distance based method. The ef- fectiveness 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.