Matches in SemOpenAlex for { <https://semopenalex.org/work/W2089894727> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2089894727 endingPage "379" @default.
- W2089894727 startingPage "357" @default.
- W2089894727 abstract "The high error rate in spontaneous speech recognition is due in part to the poor modeling of pronunciation variations. An analysis of acoustic data reveals that pronunciation variations include both complete changes and partial changes. Complete changes are the replacement of a canonical phoneme by another alternative phone, such as ‘b’ being pronounced as ‘p’. Partial changes are the variations within the phoneme, such as nasalization, centralization, voiceless, voiced, etc. Most current work in pronunciation modeling attempts to represent pronunciation variations either by alternative phonetic representations or by the concatenation of subphone units at the hidden Markov state level. In this paper, we show that partial changes are a lot less clear-cut than previously assumed and cannot be modeled by mere representation by alternate phones or a concatenation of phone units. We propose modeling partial changes through acoustic model reconstruction . We first propose a partial change phone model (PCPM) to differentiate pronunciation variations. In order to improve the model resolution without increasing the parameter size too much, PCPM is used as a hidden model and merged into the pre-trained acoustic model through model reconstruction. To avoid model confusion, auxiliary decision trees are established for PCPM triphones, and one auxiliary decision tree can only be used by one standard decision tree. The acoustic model reconstruction on triphones is equivalent to decision tree merging. The effectiveness of this approach is evaluated on the 1997 Hub4NE Mandarin Broadcast News corpus (1997 MBN) with different styles of speech. It gives a significant 2.39% syllable error rate absolute reduction in spontaneous speech." @default.
- W2089894727 created "2016-06-24" @default.
- W2089894727 creator A5028476933 @default.
- W2089894727 creator A5065856469 @default.
- W2089894727 date "2003-10-01" @default.
- W2089894727 modified "2023-09-25" @default.
- W2089894727 title "Modeling partial pronunciation variations for spontaneous Mandarin speech recognition" @default.
- W2089894727 cites W1763005514 @default.
- W2089894727 cites W1932371945 @default.
- W2089894727 cites W1992883985 @default.
- W2089894727 cites W2080723515 @default.
- W2089894727 cites W2115900267 @default.
- W2089894727 cites W2127611282 @default.
- W2089894727 cites W2127646729 @default.
- W2089894727 cites W2130628335 @default.
- W2089894727 cites W2131463853 @default.
- W2089894727 cites W2156298206 @default.
- W2089894727 cites W2164098806 @default.
- W2089894727 cites W4256346565 @default.
- W2089894727 doi "https://doi.org/10.1016/s0885-2308(03)00008-1" @default.
- W2089894727 hasPublicationYear "2003" @default.
- W2089894727 type Work @default.
- W2089894727 sameAs 2089894727 @default.
- W2089894727 citedByCount "22" @default.
- W2089894727 countsByYear W20898947272017 @default.
- W2089894727 countsByYear W20898947272021 @default.
- W2089894727 crossrefType "journal-article" @default.
- W2089894727 hasAuthorship W2089894727A5028476933 @default.
- W2089894727 hasAuthorship W2089894727A5065856469 @default.
- W2089894727 hasConcept C114614502 @default.
- W2089894727 hasConcept C138885662 @default.
- W2089894727 hasConcept C138954614 @default.
- W2089894727 hasConcept C14999030 @default.
- W2089894727 hasConcept C153180895 @default.
- W2089894727 hasConcept C154945302 @default.
- W2089894727 hasConcept C23224414 @default.
- W2089894727 hasConcept C2778707766 @default.
- W2089894727 hasConcept C2780844864 @default.
- W2089894727 hasConcept C28490314 @default.
- W2089894727 hasConcept C33923547 @default.
- W2089894727 hasConcept C40969351 @default.
- W2089894727 hasConcept C41008148 @default.
- W2089894727 hasConcept C41895202 @default.
- W2089894727 hasConcept C84525736 @default.
- W2089894727 hasConcept C87619178 @default.
- W2089894727 hasConceptScore W2089894727C114614502 @default.
- W2089894727 hasConceptScore W2089894727C138885662 @default.
- W2089894727 hasConceptScore W2089894727C138954614 @default.
- W2089894727 hasConceptScore W2089894727C14999030 @default.
- W2089894727 hasConceptScore W2089894727C153180895 @default.
- W2089894727 hasConceptScore W2089894727C154945302 @default.
- W2089894727 hasConceptScore W2089894727C23224414 @default.
- W2089894727 hasConceptScore W2089894727C2778707766 @default.
- W2089894727 hasConceptScore W2089894727C2780844864 @default.
- W2089894727 hasConceptScore W2089894727C28490314 @default.
- W2089894727 hasConceptScore W2089894727C33923547 @default.
- W2089894727 hasConceptScore W2089894727C40969351 @default.
- W2089894727 hasConceptScore W2089894727C41008148 @default.
- W2089894727 hasConceptScore W2089894727C41895202 @default.
- W2089894727 hasConceptScore W2089894727C84525736 @default.
- W2089894727 hasConceptScore W2089894727C87619178 @default.
- W2089894727 hasIssue "4" @default.
- W2089894727 hasLocation W20898947271 @default.
- W2089894727 hasOpenAccess W2089894727 @default.
- W2089894727 hasPrimaryLocation W20898947271 @default.
- W2089894727 hasRelatedWork W2029924358 @default.
- W2089894727 hasRelatedWork W2046566646 @default.
- W2089894727 hasRelatedWork W2081709028 @default.
- W2089894727 hasRelatedWork W2088167551 @default.
- W2089894727 hasRelatedWork W2089894727 @default.
- W2089894727 hasRelatedWork W2110864561 @default.
- W2089894727 hasRelatedWork W2364136279 @default.
- W2089894727 hasRelatedWork W2388979876 @default.
- W2089894727 hasRelatedWork W24638226 @default.
- W2089894727 hasRelatedWork W2588010673 @default.
- W2089894727 hasVolume "17" @default.
- W2089894727 isParatext "false" @default.
- W2089894727 isRetracted "false" @default.
- W2089894727 magId "2089894727" @default.
- W2089894727 workType "article" @default.