First European Conference on Speech Communication and Technology

Paris, France
September 27-29, 1989

DragonDictate (TM)-30K: Natural Language Speech Recognition with 30,000 Words

Janet M. Baker

Dragon Systems,Inc., Newton, MA, USA

The DragonDictate(TM)-30K automatic transcription system is a large vocabulary, discrete utterance, natural language speech recognition system. First-time users are not required to provide any initial training or enrollment speech data before using the system. Speech models for 16,000 frequent words / phrases of English are built-in. Powerful adaptation techniques dynamically build and refine up to 30,000 speech models on-line during system use. With its integration of a 80,000 word dictionary and easy introduction of new terminology, DragonDictate(TM) offers a large, open vocabulary which can be used to generate free text immediately in any discipline, however specialized. Although slower than a skilled typist, interactive users of the DragonDictate(TM) system typically create printed text more quickly by speaking than they can generate handwritten text alone. Compatible with most popular and custom software for word-processing, databases, spreadsheets, etc., DragonDictate(TM)-30K presently consists of 1 8-bit peripheral card and software, running near real-time on an MS-DOS 386-based (AT-bus), personal computer with 6 MB memory. Professionals, business executives, and other people with limited typing skills, are now independently creating their documents and reports simply by speaking them. This paper describes the features of DragonDictate(TM) from both technical and user perspectives.

Full Paper

Bibliographic reference.  Baker, Janet M. (1989): "Dragondictate (TM)-30k: natural language speech recognition with 30,000 words", In EUROSPEECH-1989, 2161-2163.