Matches in SemOpenAlex for { <https://semopenalex.org/work/W2097331808> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2097331808 abstract "We propose a new speech recognition method (HMM-trajectory method) that generates a speech trajectory from HMMs by maximizing their likelihood while accounting for the relationship between the MFCCs and dynamic MFCCs. One major advantage of this method is that this relationship, ignored in conventional speech recognition, is directly used in the speech recognition phase. This paper improves the recognition performance of the HMM-trajectory method for dealing with mixture Gaussian distributions. While the HMM-trajectory method chooses the Gaussian distribution sequence of the HMM states by selecting the best Gaussian distribution in the state during Viterbi decoding and calculating HMM trajectory likelihood along with the sequence, the proposed method compensates for HMM trajectory likelihood using ordinary HMM likelihood. In speaker-independent speech recognition experiments, the proposed method reduced the error rate about 10% for the task compared with HMMs, proving its effectiveness for Gaussian mixture components." @default.
- W2097331808 created "2016-06-24" @default.
- W2097331808 creator A5008413640 @default.
- W2097331808 date "2007-01-01" @default.
- W2097331808 modified "2023-10-14" @default.
- W2097331808 title "Mixture Gaussian HMM-trajctory method using likelihood compensation" @default.
- W2097331808 cites W109008040 @default.
- W2097331808 cites W1853111913 @default.
- W2097331808 cites W1935012542 @default.
- W2097331808 cites W2020335243 @default.
- W2097331808 cites W2081309747 @default.
- W2097331808 cites W2118825896 @default.
- W2097331808 cites W2125107595 @default.
- W2097331808 cites W2149361029 @default.
- W2097331808 cites W2159501365 @default.
- W2097331808 cites W2465919943 @default.
- W2097331808 cites W3150863438 @default.
- W2097331808 doi "https://doi.org/10.1109/asru.2007.4430127" @default.
- W2097331808 hasPublicationYear "2007" @default.
- W2097331808 type Work @default.
- W2097331808 sameAs 2097331808 @default.
- W2097331808 citedByCount "0" @default.
- W2097331808 crossrefType "proceedings-article" @default.
- W2097331808 hasAuthorship W2097331808A5008413640 @default.
- W2097331808 hasConcept C11413529 @default.
- W2097331808 hasConcept C121332964 @default.
- W2097331808 hasConcept C1276947 @default.
- W2097331808 hasConcept C13662910 @default.
- W2097331808 hasConcept C153180895 @default.
- W2097331808 hasConcept C154945302 @default.
- W2097331808 hasConcept C163716315 @default.
- W2097331808 hasConcept C23224414 @default.
- W2097331808 hasConcept C2778112365 @default.
- W2097331808 hasConcept C28490314 @default.
- W2097331808 hasConcept C41008148 @default.
- W2097331808 hasConcept C54355233 @default.
- W2097331808 hasConcept C57273362 @default.
- W2097331808 hasConcept C60582962 @default.
- W2097331808 hasConcept C61224824 @default.
- W2097331808 hasConcept C61326573 @default.
- W2097331808 hasConcept C62520636 @default.
- W2097331808 hasConcept C86803240 @default.
- W2097331808 hasConceptScore W2097331808C11413529 @default.
- W2097331808 hasConceptScore W2097331808C121332964 @default.
- W2097331808 hasConceptScore W2097331808C1276947 @default.
- W2097331808 hasConceptScore W2097331808C13662910 @default.
- W2097331808 hasConceptScore W2097331808C153180895 @default.
- W2097331808 hasConceptScore W2097331808C154945302 @default.
- W2097331808 hasConceptScore W2097331808C163716315 @default.
- W2097331808 hasConceptScore W2097331808C23224414 @default.
- W2097331808 hasConceptScore W2097331808C2778112365 @default.
- W2097331808 hasConceptScore W2097331808C28490314 @default.
- W2097331808 hasConceptScore W2097331808C41008148 @default.
- W2097331808 hasConceptScore W2097331808C54355233 @default.
- W2097331808 hasConceptScore W2097331808C57273362 @default.
- W2097331808 hasConceptScore W2097331808C60582962 @default.
- W2097331808 hasConceptScore W2097331808C61224824 @default.
- W2097331808 hasConceptScore W2097331808C61326573 @default.
- W2097331808 hasConceptScore W2097331808C62520636 @default.
- W2097331808 hasConceptScore W2097331808C86803240 @default.
- W2097331808 hasLocation W20973318081 @default.
- W2097331808 hasOpenAccess W2097331808 @default.
- W2097331808 hasPrimaryLocation W20973318081 @default.
- W2097331808 hasRelatedWork W1541505381 @default.
- W2097331808 hasRelatedWork W1542418153 @default.
- W2097331808 hasRelatedWork W2040126760 @default.
- W2097331808 hasRelatedWork W2069705557 @default.
- W2097331808 hasRelatedWork W2096698602 @default.
- W2097331808 hasRelatedWork W2116106600 @default.
- W2097331808 hasRelatedWork W2147207799 @default.
- W2097331808 hasRelatedWork W2155089829 @default.
- W2097331808 hasRelatedWork W2304768685 @default.
- W2097331808 hasRelatedWork W2402332480 @default.
- W2097331808 isParatext "false" @default.
- W2097331808 isRetracted "false" @default.
- W2097331808 magId "2097331808" @default.
- W2097331808 workType "article" @default.