A CACHE-BASED NATURAL-LANGUAGE MODEL FOR SPEECH RECOGNITION

Speech recognition systems must often decide between competing ways of breaking up the acoustic input into strings of words. Since the possible strings may be acoustically similar, a language model is required; given a word string, the model returns its linguistic probability. This paper discusses several Markov language models. Subsequently, we present a new kind of language model which reflects short-term patterns of word use by means of a “cache component,” analogous to “cache memory” in hardware terminology. The model also contains a “3g-gram component” of the traditional type. The combined model and a pure 3g-gram model were tested on samples drawn from the LOB (Lancaster-Oslo/Bergen) corpus of English text. We discuss the relative performance of the two models, and make suggestions for future improvements. © 1990 IEEE