Issue No. 06 - June (1990 vol. 12)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.56193
<p>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. Several Markov language models are discussed. A novel 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) is presented. 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 Lancaster-Oslo/Bergen (LOB) corpus of English text. The relative performance of the two models is examined, and suggestions for the future improvements are made.</p>
cache-based natural language model; speech recognition; word string; linguistic probability; Markov language models; Lancaster-Oslo/Bergen; English text; Markov processes; natural languages; probability; speech recognition
R. De Mori and R. Kuhn, "A Cache-Based Natural Language Model for Speech Recognition," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 12, no. , pp. 570-583, 1990.