Matches in SemOpenAlex for { <https://semopenalex.org/work/W1535536467> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W1535536467 abstract "The conventional hidden Markov model (HMM) only based on the spectral features does not have a high recognition performance for connected Mandarin digits, because highly confusable syllables exist. The main problems of Mandarin digit recognition are analyzed. It is revealed that to establish the precise classification models for Mandarin digits not only features extracted from the spectrum, energy and pitch contour are necessary but also they should be used with different emphases for different digits. So each-type of feature is used to train a single-stream HMM by maximum likelihood. Then a multi-stream HMM is obtained by combining the single-stream HMMs with exponents that weigh the log-likelihood of each stream. The exponents are estimated by means of the generalized probabilistic descent algorithm according to the digit minimum classification error rate criteria. The superiority of the multi-stream HMM is demonstrated: the relative string error rate is reduced by 54.5%. And the unknown length digit string error rate and its digit error rate decrease to 4.66% and 1.31% respectively." @default.
- W1535536467 created "2016-06-24" @default.
- W1535536467 creator A5034981144 @default.
- W1535536467 creator A5057117256 @default.
- W1535536467 creator A5076539835 @default.
- W1535536467 date "2003-08-27" @default.
- W1535536467 modified "2023-10-06" @default.
- W1535536467 title "Discriminative HMM stream model for Mandarin digit string speech recognition" @default.
- W1535536467 cites W1829217008 @default.
- W1535536467 cites W2133906911 @default.
- W1535536467 cites W2158289097 @default.
- W1535536467 doi "https://doi.org/10.1109/icosp.2002.1181109" @default.
- W1535536467 hasPublicationYear "2003" @default.
- W1535536467 type Work @default.
- W1535536467 sameAs 1535536467 @default.
- W1535536467 citedByCount "3" @default.
- W1535536467 crossrefType "proceedings-article" @default.
- W1535536467 hasAuthorship W1535536467A5034981144 @default.
- W1535536467 hasAuthorship W1535536467A5057117256 @default.
- W1535536467 hasAuthorship W1535536467A5076539835 @default.
- W1535536467 hasConcept C138885662 @default.
- W1535536467 hasConcept C138954614 @default.
- W1535536467 hasConcept C153180895 @default.
- W1535536467 hasConcept C154945302 @default.
- W1535536467 hasConcept C157486923 @default.
- W1535536467 hasConcept C23224414 @default.
- W1535536467 hasConcept C28490314 @default.
- W1535536467 hasConcept C2984784707 @default.
- W1535536467 hasConcept C33923547 @default.
- W1535536467 hasConcept C37914503 @default.
- W1535536467 hasConcept C40969351 @default.
- W1535536467 hasConcept C41008148 @default.
- W1535536467 hasConcept C41895202 @default.
- W1535536467 hasConcept C50644808 @default.
- W1535536467 hasConcept C97931131 @default.
- W1535536467 hasConceptScore W1535536467C138885662 @default.
- W1535536467 hasConceptScore W1535536467C138954614 @default.
- W1535536467 hasConceptScore W1535536467C153180895 @default.
- W1535536467 hasConceptScore W1535536467C154945302 @default.
- W1535536467 hasConceptScore W1535536467C157486923 @default.
- W1535536467 hasConceptScore W1535536467C23224414 @default.
- W1535536467 hasConceptScore W1535536467C28490314 @default.
- W1535536467 hasConceptScore W1535536467C2984784707 @default.
- W1535536467 hasConceptScore W1535536467C33923547 @default.
- W1535536467 hasConceptScore W1535536467C37914503 @default.
- W1535536467 hasConceptScore W1535536467C40969351 @default.
- W1535536467 hasConceptScore W1535536467C41008148 @default.
- W1535536467 hasConceptScore W1535536467C41895202 @default.
- W1535536467 hasConceptScore W1535536467C50644808 @default.
- W1535536467 hasConceptScore W1535536467C97931131 @default.
- W1535536467 hasLocation W15355364671 @default.
- W1535536467 hasOpenAccess W1535536467 @default.
- W1535536467 hasPrimaryLocation W15355364671 @default.
- W1535536467 hasRelatedWork W1523934345 @default.
- W1535536467 hasRelatedWork W1765418723 @default.
- W1535536467 hasRelatedWork W1886400913 @default.
- W1535536467 hasRelatedWork W1965307992 @default.
- W1535536467 hasRelatedWork W2012963025 @default.
- W1535536467 hasRelatedWork W2040216096 @default.
- W1535536467 hasRelatedWork W2064844706 @default.
- W1535536467 hasRelatedWork W2096075540 @default.
- W1535536467 hasRelatedWork W2097331808 @default.
- W1535536467 hasRelatedWork W2101191963 @default.
- W1535536467 hasRelatedWork W2108105213 @default.
- W1535536467 hasRelatedWork W2114016253 @default.
- W1535536467 hasRelatedWork W2121986117 @default.
- W1535536467 hasRelatedWork W2129422402 @default.
- W1535536467 hasRelatedWork W2137944862 @default.
- W1535536467 hasRelatedWork W2138104808 @default.
- W1535536467 hasRelatedWork W2146049072 @default.
- W1535536467 hasRelatedWork W2153500048 @default.
- W1535536467 hasRelatedWork W2964273407 @default.
- W1535536467 hasRelatedWork W2880853900 @default.
- W1535536467 isParatext "false" @default.
- W1535536467 isRetracted "false" @default.
- W1535536467 magId "1535536467" @default.
- W1535536467 workType "article" @default.