Improving the suitability of imperfect transcriptions for information retrieval from spoken documents

Recently there has been a considerable focus on information retrieval for multimedia databases. When speech is used as the source material for multimedia indexing, the effect of transcriber error on retrieval effectiveness must be considered. This paper describes a method for measuring the relevance of documents to queries when information about the probability of word transcription error is available. To support the use of this technique, a method is presented for estimating word error probability in speech recognition engines that use word graphs (lattices). An information retrieval experiment using this technique on a large corpus of spoken documents is discussed. The method was able to reduce the difference in retrieval effectiveness between reference texts and hypothesized texts by 13%-38% depending on the size of the document set.