1995 International Conference on Acoustics, Speech, and Signal Processing
DOI: 10.1109/icassp.1995.479272
|View full text |Cite
|
Sign up to set email alerts
|

Golden Mandarin (III)-a user-adaptive prosodic-segment-based Mandarin dictation machine for Chinese language with very large vocabulary

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 12 publications
(2 citation statements)
references
References 7 publications
0
2
0
Order By: Relevance
“…On these digitized speech the LPC analysis is performed to prepare appropriate feature vectors for the acoustic modeling of 416 base syllables and 5 lexical tones; i.e., 149 intrasyllable right-context-dependent (RCD) phone-like units for base syllable [1] and 23 context-dependent models for tone [2]. Speech of isolated syllables and phonetically balanced sentences from 40 male speakers is used to train the speaker-independent acoustic model.…”
Section: Speech Databasementioning
confidence: 99%
See 1 more Smart Citation
“…On these digitized speech the LPC analysis is performed to prepare appropriate feature vectors for the acoustic modeling of 416 base syllables and 5 lexical tones; i.e., 149 intrasyllable right-context-dependent (RCD) phone-like units for base syllable [1] and 23 context-dependent models for tone [2]. Speech of isolated syllables and phonetically balanced sentences from 40 male speakers is used to train the speaker-independent acoustic model.…”
Section: Speech Databasementioning
confidence: 99%
“…Consider, for example [1] [2], the speech recognizer with the twostaged architecture. First the syllable lattice is prepared by the use of Viterbi algorithm, then out of the syllable lattice a word lattice is constructed with the help of lexical access, and finally a linguistic decoder is employed to find the best word sequence as the recognition result.…”
Section: Introductionmentioning
confidence: 99%