A Commercial Large-Vocabulary Discrete Speech Recognition System: DragonDictate | Zendy

Mark A. Mandel | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

A Commercial Large-Vocabulary Discrete Speech Recognition System: DragonDictate

Author(s) -

Mark A. Mandel

Publication year - 1992

Publication title -

language and speech

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.713

H-Index - 52

eISSN - 1756-6053

pISSN - 0023-8309

DOI - 10.1177/002383099203500218

Subject(s) - speech recognition , computer science , vocabulary , hidden markov model , context (archaeology) , phonology , speech production , word (group theory) , production (economics) , natural language processing , speech corpus , artificial intelligence , linguistics , speech synthesis , paleontology , philosophy , macroeconomics , economics , biology

DragonDictate is currently the only commercially available general-purpose, large-vocabulary speech recognition system. It uses discrete speech and is speaker-dependent, adapting to the speaker's voice and language model with every word. Its acoustic adaptability is based in a three-level phonology and a stochastic model of production. The phonological levels are phonemes, augmented triphones (phonemes-in-context or PICs), and steady-state spectral slices that are concatenated to approximate the spectra of these PICs (phonetic elements or PELs) and thus of words. Production is treated as a hidden Markov process, which the recognizer has to identify from its output, the spoken word. Findings of practical value to speech recognition are presented from research on six European languages.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research