Matches in SemOpenAlex for { <https://semopenalex.org/work/W2107426051> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2107426051 endingPage "2856" @default.
- W2107426051 startingPage "2849" @default.
- W2107426051 abstract "In conventional Vector Taylor Series (VTS) based noisy speech recognition methods, Hidden Markov Models (HMMs) are trained using clean speech, and the parameters of the clean speech HMM are adapted to test noisy speech, or the original clean speech is estimated from the test noisy speech. However, these approaches have a drawback in that acoustic models trained using noisy speech cannot be used in recognition. In noisy speech recognition, improved performance is generally expected by employing noisy acoustic models produced by methods such as Multi-condition Training (MTR) and Multi-Model-based Speech Recognition framework (MMSR). Motivated by this idea, a method has been developed that can make use of the noisy acoustic models in the VTS algorithm where additive noise was adapted for the speech feature compensation. In this paper, we modified the previous method to adapt channel noise as well as additive noise. A mathematical relation was derived in the log-spectrum domain between the test and training noisy speech considering both channel and additive noise. After approximating the relation using VTS, Minimum Mean Square Error (MMSE) estimation of the training noisy speech is obtained from the test noisy speech based on the relation. The proposed method was applied to noisy speech HMMs trained by MTR and MMSR and cou ld reduce the relative word error rate by 7% and 8%, respectively, in the noisy speech recognition experiments on the Aurora 2 database." @default.
- W2107426051 created "2016-06-24" @default.
- W2107426051 creator A5070004655 @default.
- W2107426051 date "2014-11-01" @default.
- W2107426051 modified "2023-09-26" @default.
- W2107426051 title "A VTS-based Feature Compensation Method using Noisy Speech HMMs" @default.
- W2107426051 cites W105750483 @default.
- W2107426051 cites W1573570773 @default.
- W2107426051 cites W1665196592 @default.
- W2107426051 cites W2010023285 @default.
- W2107426051 cites W2080921589 @default.
- W2107426051 cites W2094709280 @default.
- W2107426051 cites W2120011474 @default.
- W2107426051 cites W2128653836 @default.
- W2107426051 cites W2136439176 @default.
- W2107426051 cites W2137401359 @default.
- W2107426051 cites W2151484683 @default.
- W2107426051 cites W2162213734 @default.
- W2107426051 cites W2169967551 @default.
- W2107426051 cites W2172115193 @default.
- W2107426051 cites W589191 @default.
- W2107426051 doi "https://doi.org/10.12785/amis/080621" @default.
- W2107426051 hasPublicationYear "2014" @default.
- W2107426051 type Work @default.
- W2107426051 sameAs 2107426051 @default.
- W2107426051 citedByCount "0" @default.
- W2107426051 crossrefType "journal-article" @default.
- W2107426051 hasAuthorship W2107426051A5070004655 @default.
- W2107426051 hasConcept C11171543 @default.
- W2107426051 hasConcept C138885662 @default.
- W2107426051 hasConcept C153180895 @default.
- W2107426051 hasConcept C154945302 @default.
- W2107426051 hasConcept C15744967 @default.
- W2107426051 hasConcept C23224414 @default.
- W2107426051 hasConcept C2776401178 @default.
- W2107426051 hasConcept C2780023022 @default.
- W2107426051 hasConcept C28490314 @default.
- W2107426051 hasConcept C41008148 @default.
- W2107426051 hasConcept C41895202 @default.
- W2107426051 hasConceptScore W2107426051C11171543 @default.
- W2107426051 hasConceptScore W2107426051C138885662 @default.
- W2107426051 hasConceptScore W2107426051C153180895 @default.
- W2107426051 hasConceptScore W2107426051C154945302 @default.
- W2107426051 hasConceptScore W2107426051C15744967 @default.
- W2107426051 hasConceptScore W2107426051C23224414 @default.
- W2107426051 hasConceptScore W2107426051C2776401178 @default.
- W2107426051 hasConceptScore W2107426051C2780023022 @default.
- W2107426051 hasConceptScore W2107426051C28490314 @default.
- W2107426051 hasConceptScore W2107426051C41008148 @default.
- W2107426051 hasConceptScore W2107426051C41895202 @default.
- W2107426051 hasIssue "6" @default.
- W2107426051 hasLocation W21074260511 @default.
- W2107426051 hasOpenAccess W2107426051 @default.
- W2107426051 hasPrimaryLocation W21074260511 @default.
- W2107426051 hasRelatedWork W1507687735 @default.
- W2107426051 hasRelatedWork W2023185280 @default.
- W2107426051 hasRelatedWork W2100982643 @default.
- W2107426051 hasRelatedWork W2116511732 @default.
- W2107426051 hasRelatedWork W2146992157 @default.
- W2107426051 hasRelatedWork W2374918184 @default.
- W2107426051 hasRelatedWork W2375321655 @default.
- W2107426051 hasRelatedWork W2539985974 @default.
- W2107426051 hasRelatedWork W3128571556 @default.
- W2107426051 hasRelatedWork W4301681594 @default.
- W2107426051 hasVolume "8" @default.
- W2107426051 isParatext "false" @default.
- W2107426051 isRetracted "false" @default.
- W2107426051 magId "2107426051" @default.
- W2107426051 workType "article" @default.