HWIM, a natural language speech understander

New advances have been made in automatic speech recognition. HWIM, the speech understanding system developed at BBN as part of the recent five-year ARPA Speech Understanding Research Project, is designed to "understand" naturally spoken utterances relevant to a task domain of travel budget management. Its vocabulary is over 1000 words, and its grammar permits a relatively habitable subset of natural English. HWIM contains sources of knowledge at the levels of acoustic-phonetics, phonology, vocabulary, syntax, semantics, factual knowledge, and discourse. In October 1976, HWIM achieved 44% sentence accuracy on a test set of utterances by three male speakers. This paper describes how such knowledge sources are implemented and used to understand speech.