New word detection in audio-indexing

For an audio indexing system that uses a speech recognizer with a fixed vocabulary to be practical, one needs the ability to detect out of vocabulary or new words at query time. We present a fast, vocabulary independent algorithm for spotting words in speech. The algorithm consists of a preprocessing stage and a coarse to detailed search strategy for spotting a word/phone sequence in speech. The preprocessing method provides a phone level representation of the speech that can be searched efficiently. The coarse search, consisting of phone-ngram matching, identifies regions of speech as putative word hits. The detailed acoustic match is then conducted only at the putative hits identified in the coarse match. This gives us the desired speed in wordspotting.