Matches in SemOpenAlex for { <https://semopenalex.org/work/W10800834> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W10800834 abstract "This paper describes a novel approach to flexible control of speaker characteristics using tensor representation of speaker space. In voice conversion studies, realization of conversion from/to an arbitrary speaker’s voice is one of the important objectives. For this purpose, eigenvoice conversion (EVC) based on an eigenvoice Gaussian mixture model (EV-GMM) was proposed. In the EVC, similarly to speaker recognition approaches, a speaker space is constructed based on GMM supervectors which are high-dimensional vectors derived by concatenating the mean vectors of each of the speaker GMMs. In the speaker space, each speaker is represented by a small number of weight parameters of eigen-supervectors. In this paper, we revisit construction of the speaker space by introducing the tensor analysis of training data set. In our approach, each speaker is represented as a matrix of which the row and the column respectively correspond to the Gaussian component and the dimension of the mean vector, and the speaker space is derived by the tensor analysis of the set of the matrices. Our approach can solve an inherent problem of supervector representation, and it improves the performance of voice conversion. Experimental results of oneto-many voice conversion demonstrate the effectiveness of the proposed approach. Index Terms: voice conversion, Gaussian mixture model, eigenvoice, tensor analysis, Tucker decomposition" @default.
- W10800834 created "2016-06-24" @default.
- W10800834 creator A5010841595 @default.
- W10800834 creator A5035369256 @default.
- W10800834 creator A5041213266 @default.
- W10800834 creator A5078386192 @default.
- W10800834 date "2011-08-27" @default.
- W10800834 modified "2023-10-16" @default.
- W10800834 title "One-to-many voice conversion based on tensor representation of speaker space" @default.
- W10800834 cites W1588266896 @default.
- W10800834 cites W1603790919 @default.
- W10800834 cites W17772838 @default.
- W10800834 cites W1950777589 @default.
- W10800834 cites W1963826206 @default.
- W10800834 cites W1965255698 @default.
- W10800834 cites W2007023536 @default.
- W10800834 cites W2009377577 @default.
- W10800834 cites W2009396100 @default.
- W10800834 cites W2013912476 @default.
- W10800834 cites W2049686551 @default.
- W10800834 cites W2113055885 @default.
- W10800834 cites W2118850452 @default.
- W10800834 cites W2120605154 @default.
- W10800834 cites W2123003832 @default.
- W10800834 cites W2126143605 @default.
- W10800834 cites W2136879537 @default.
- W10800834 cites W2153057929 @default.
- W10800834 cites W2156142001 @default.
- W10800834 cites W2165108269 @default.
- W10800834 cites W49412823 @default.
- W10800834 doi "https://doi.org/10.21437/interspeech.2011-268" @default.
- W10800834 hasPublicationYear "2011" @default.
- W10800834 type Work @default.
- W10800834 sameAs 10800834 @default.
- W10800834 citedByCount "59" @default.
- W10800834 countsByYear W108008342012 @default.
- W10800834 countsByYear W108008342013 @default.
- W10800834 countsByYear W108008342014 @default.
- W10800834 countsByYear W108008342015 @default.
- W10800834 countsByYear W108008342016 @default.
- W10800834 countsByYear W108008342017 @default.
- W10800834 countsByYear W108008342018 @default.
- W10800834 countsByYear W108008342019 @default.
- W10800834 countsByYear W108008342020 @default.
- W10800834 countsByYear W108008342022 @default.
- W10800834 countsByYear W108008342023 @default.
- W10800834 crossrefType "proceedings-article" @default.
- W10800834 hasAuthorship W10800834A5010841595 @default.
- W10800834 hasAuthorship W10800834A5035369256 @default.
- W10800834 hasAuthorship W10800834A5041213266 @default.
- W10800834 hasAuthorship W10800834A5078386192 @default.
- W10800834 hasBestOaLocation W108008342 @default.
- W10800834 hasConcept C111919701 @default.
- W10800834 hasConcept C133892786 @default.
- W10800834 hasConcept C149838564 @default.
- W10800834 hasConcept C155281189 @default.
- W10800834 hasConcept C17744445 @default.
- W10800834 hasConcept C199539241 @default.
- W10800834 hasConcept C202444582 @default.
- W10800834 hasConcept C2776359362 @default.
- W10800834 hasConcept C2778572836 @default.
- W10800834 hasConcept C28490314 @default.
- W10800834 hasConcept C33923547 @default.
- W10800834 hasConcept C41008148 @default.
- W10800834 hasConcept C94625758 @default.
- W10800834 hasConceptScore W10800834C111919701 @default.
- W10800834 hasConceptScore W10800834C133892786 @default.
- W10800834 hasConceptScore W10800834C149838564 @default.
- W10800834 hasConceptScore W10800834C155281189 @default.
- W10800834 hasConceptScore W10800834C17744445 @default.
- W10800834 hasConceptScore W10800834C199539241 @default.
- W10800834 hasConceptScore W10800834C202444582 @default.
- W10800834 hasConceptScore W10800834C2776359362 @default.
- W10800834 hasConceptScore W10800834C2778572836 @default.
- W10800834 hasConceptScore W10800834C28490314 @default.
- W10800834 hasConceptScore W10800834C33923547 @default.
- W10800834 hasConceptScore W10800834C41008148 @default.
- W10800834 hasConceptScore W10800834C94625758 @default.
- W10800834 hasLocation W108008341 @default.
- W10800834 hasLocation W108008342 @default.
- W10800834 hasOpenAccess W10800834 @default.
- W10800834 hasPrimaryLocation W108008341 @default.
- W10800834 hasRelatedWork W1497807607 @default.
- W10800834 hasRelatedWork W1509309911 @default.
- W10800834 hasRelatedWork W1521049138 @default.
- W10800834 hasRelatedWork W1813780412 @default.
- W10800834 hasRelatedWork W2128773298 @default.
- W10800834 hasRelatedWork W2144208207 @default.
- W10800834 hasRelatedWork W2162158162 @default.
- W10800834 hasRelatedWork W2312116756 @default.
- W10800834 hasRelatedWork W2499802997 @default.
- W10800834 hasRelatedWork W2175373321 @default.
- W10800834 isParatext "false" @default.
- W10800834 isRetracted "false" @default.
- W10800834 magId "10800834" @default.
- W10800834 workType "article" @default.