A fully parallel Mandarin speech recognition system with very large vocabulary and almost unlimited texts
Resource
Circuits and Systems, 1991., IEEE International Sympoisum on
Journal
IEEE International Symposium on Circuits and Systems, 1991
Pages
-
Date Issued
1991-06
Date
1991-06
Author(s)
DOI
N/A
Abstract
The authors describe a fully parallel real-time Mandarin dictation machine which recognizes Mandarin speech with almost unlimited texts and a very large vocabulary for the input of Chinese characters to computers. Isolated syllables including the tones are first recognized using specially trained hidden Markov models with special feature parameters, and the exact characters are then identified from the syllables using a Markov Chinese language model, because every syllable can represent many different homonym characters. The real-time implementation is in Occam language on a transputer system with 10 T800 processors operating in parallel. The overall correction rate for the final output characters is about 80%.>
SDGs
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
00176401.pdf
Size
519.86 KB
Format
Adobe PDF
Checksum
(MD5):bd42d8a36cea464f52668aa27aa55bac