Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321374109> ?p ?o ?g. }
- W4321374109 endingPage "375" @default.
- W4321374109 startingPage "375" @default.
- W4321374109 abstract "Voice conversion (VC) consists of digitally altering the voice of an individual to manipulate part of its content, primarily its identity, while maintaining the rest unchanged. Research in neural VC has accomplished considerable breakthroughs with the capacity to falsify a voice identity using a small amount of data with a highly realistic rendering. This paper goes beyond voice identity manipulation and presents an original neural architecture that allows the manipulation of voice attributes (e.g., gender and age). The proposed architecture is inspired by the fader network, transferring the same ideas to voice manipulation. The information conveyed by the speech signal is disentangled into interpretative voice attributes by means of minimizing adversarial loss to make the encoded information mutually independent while preserving the capacity to generate a speech signal from the disentangled codes. During inference for voice conversion, the disentangled voice attributes can be manipulated and the speech signal can be generated accordingly. For experimental evaluation, the proposed method is applied to the task of voice gender conversion using the freely available VCTK dataset. Quantitative measurements of mutual information between the variables of speaker identity and speaker gender show that the proposed architecture can learn gender-independent representation of speakers. Additional measurements of speaker recognition indicate that speaker identity can be recognized accurately from the gender-independent representation. Finally, a subjective experiment conducted on the task of voice gender manipulation shows that the proposed architecture can convert voice gender with very high efficiency and good naturalness." @default.
- W4321374109 created "2023-02-21" @default.
- W4321374109 creator A5016340271 @default.
- W4321374109 creator A5042745853 @default.
- W4321374109 creator A5065828059 @default.
- W4321374109 date "2023-02-18" @default.
- W4321374109 modified "2023-09-26" @default.
- W4321374109 title "Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations" @default.
- W4321374109 cites W122750681 @default.
- W4321374109 cites W2007023536 @default.
- W4321374109 cites W2011916518 @default.
- W4321374109 cites W2056133372 @default.
- W4321374109 cites W2059138330 @default.
- W4321374109 cites W2120847449 @default.
- W4321374109 cites W2126143605 @default.
- W4321374109 cites W2156142001 @default.
- W4321374109 cites W2473388484 @default.
- W4321374109 cites W2518172956 @default.
- W4321374109 cites W2532494225 @default.
- W4321374109 cites W2888470020 @default.
- W4321374109 cites W2889329491 @default.
- W4321374109 cites W2899877258 @default.
- W4321374109 cites W2902070858 @default.
- W4321374109 cites W2937579788 @default.
- W4321374109 cites W2962793481 @default.
- W4321374109 cites W2963035245 @default.
- W4321374109 cites W2963300588 @default.
- W4321374109 cites W2963539064 @default.
- W4321374109 cites W2963767194 @default.
- W4321374109 cites W2964069186 @default.
- W4321374109 cites W2964195110 @default.
- W4321374109 cites W2972399707 @default.
- W4321374109 cites W2972473628 @default.
- W4321374109 cites W2972667718 @default.
- W4321374109 cites W2973154337 @default.
- W4321374109 cites W3005862564 @default.
- W4321374109 cites W3015707856 @default.
- W4321374109 cites W3034420534 @default.
- W4321374109 cites W3101689408 @default.
- W4321374109 cites W3104940529 @default.
- W4321374109 cites W4281619582 @default.
- W4321374109 doi "https://doi.org/10.3390/e25020375" @default.
- W4321374109 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36832741" @default.
- W4321374109 hasPublicationYear "2023" @default.
- W4321374109 type Work @default.
- W4321374109 citedByCount "0" @default.
- W4321374109 crossrefType "journal-article" @default.
- W4321374109 hasAuthorship W4321374109A5016340271 @default.
- W4321374109 hasAuthorship W4321374109A5042745853 @default.
- W4321374109 hasAuthorship W4321374109A5065828059 @default.
- W4321374109 hasBestOaLocation W43213741091 @default.
- W4321374109 hasConcept C121332964 @default.
- W4321374109 hasConcept C133892786 @default.
- W4321374109 hasConcept C134537474 @default.
- W4321374109 hasConcept C154945302 @default.
- W4321374109 hasConcept C162324750 @default.
- W4321374109 hasConcept C17744445 @default.
- W4321374109 hasConcept C187736073 @default.
- W4321374109 hasConcept C199539241 @default.
- W4321374109 hasConcept C204321447 @default.
- W4321374109 hasConcept C205711294 @default.
- W4321374109 hasConcept C24890656 @default.
- W4321374109 hasConcept C2776214188 @default.
- W4321374109 hasConcept C2776359362 @default.
- W4321374109 hasConcept C2778355321 @default.
- W4321374109 hasConcept C2780451532 @default.
- W4321374109 hasConcept C28490314 @default.
- W4321374109 hasConcept C41008148 @default.
- W4321374109 hasConcept C62520636 @default.
- W4321374109 hasConcept C94625758 @default.
- W4321374109 hasConceptScore W4321374109C121332964 @default.
- W4321374109 hasConceptScore W4321374109C133892786 @default.
- W4321374109 hasConceptScore W4321374109C134537474 @default.
- W4321374109 hasConceptScore W4321374109C154945302 @default.
- W4321374109 hasConceptScore W4321374109C162324750 @default.
- W4321374109 hasConceptScore W4321374109C17744445 @default.
- W4321374109 hasConceptScore W4321374109C187736073 @default.
- W4321374109 hasConceptScore W4321374109C199539241 @default.
- W4321374109 hasConceptScore W4321374109C204321447 @default.
- W4321374109 hasConceptScore W4321374109C205711294 @default.
- W4321374109 hasConceptScore W4321374109C24890656 @default.
- W4321374109 hasConceptScore W4321374109C2776214188 @default.
- W4321374109 hasConceptScore W4321374109C2776359362 @default.
- W4321374109 hasConceptScore W4321374109C2778355321 @default.
- W4321374109 hasConceptScore W4321374109C2780451532 @default.
- W4321374109 hasConceptScore W4321374109C28490314 @default.
- W4321374109 hasConceptScore W4321374109C41008148 @default.
- W4321374109 hasConceptScore W4321374109C62520636 @default.
- W4321374109 hasConceptScore W4321374109C94625758 @default.
- W4321374109 hasFunder F4320320883 @default.
- W4321374109 hasIssue "2" @default.
- W4321374109 hasLocation W43213741091 @default.
- W4321374109 hasLocation W43213741092 @default.
- W4321374109 hasLocation W43213741093 @default.
- W4321374109 hasLocation W43213741094 @default.
- W4321374109 hasOpenAccess W4321374109 @default.
- W4321374109 hasPrimaryLocation W43213741091 @default.
- W4321374109 hasRelatedWork W2007171027 @default.