Abstract

Generic recognition systems contain language models which are representative of a broad corpus. In actual practice, however, recognition is usually on a coherent text covering a single topic, suggesting that knowledge of the topic at hand can be used to advantage. A base model can be augmented with information from a small sample of domain-specific language data to significantly improve recognition performance. Good performance may be obtained by merging in only those n-grams that include words that are out of vocabulary with respect to the base model. 1. Introduction Current language modeling practice requires access to a substantial amount of text from a target domain in order to create a reliable language model. For the North American Business (CSR NAB) domain, 227M words were available. Of necessity models based on large corpora cover a diversity of material and are fairly general in nature. In practice, a given sequence of input utterances (say a dictation) will stick to a parti...

Citations

154	Adaptive Statistical Language Modeling: A Maximum Entropy Approach - Rosenfeld - 1994
19	Design of the 1994 CSR Benchmark Tests - Kubala - 1995
10	Classifying words for improved statistical language models - Jelinek, Mercer, et al. - 1990
1	Improvements in language, lexical and phonetic modeling - CHASE, ROSENFELD, et al. - 1995
1	A cache-basednatural language model for speech recognition - KUHN, ANDMORI - 1990
1	The 1994 BU WSJ benchmark system - OSTENDORF, RICHARDSON, et al. - 1995
1	CSR evaluation - SEKINE, STERLING, et al. - 1994