FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312994048> ?p ?o ?g. }

• W4312994048 endingPage "134037" @default.
• W4312994048 startingPage "134029" @default.
• W4312994048 abstract "We propose a joint training scheme of an any-to-one voice conversion (VC) system with LPCNet to improve the speech naturalness, speaker similarity, and intelligibility of the converted speech. Recent advancements in neural-based vocoders, such as LPCNet, have enabled the production of more natural and clear speech. However, other components in typical VC systems are often designed independently, such as the conversion model. Hence, separate training strategies are used for each component that is not in direct correlation to the training objective of the vocoder preventing exploitation of the full potential of LPCNet. This problem is addressed by proposing a jointly trained conversion model and LPCNet. To accurately capture the linguistic contents of the given utterance, we use speaker-independent (SI) features derived from an automatic speech recognition (ASR) model trained using a mixed-language speech corpus. Subsequently, a conversion model maps the SI features to the acoustic representations used as input features to LPCNet. The possibility to synthesize cross-language speech using the proposed approach is also explored in this paper. Experimental results show that the proposed model can achieve real-time VC, unlocking the full potential of LPCNet and outperforming the state of the art." @default.
• W4312994048 created "2023-01-05" @default.
• W4312994048 creator A5007826853 @default.
• W4312994048 creator A5034095159 @default.
• W4312994048 creator A5039529498 @default.
• W4312994048 creator A5055128383 @default.
• W4312994048 date "2022-01-01" @default.
• W4312994048 modified "2023-10-14" @default.
• W4312994048 title "Jointly Trained Conversion Model With LPCNet for Any-to-One Voice Conversion Using Speaker-Independent Linguistic Features" @default.
• W4312994048 cites W1970890968 @default.
• W4312994048 cites W1983424905 @default.
• W4312994048 cites W2105160541 @default.
• W4312994048 cites W2120605154 @default.
• W4312994048 cites W2131774270 @default.
• W4312994048 cites W2142300631 @default.
• W4312994048 cites W2156142001 @default.
• W4312994048 cites W2406799407 @default.
• W4312994048 cites W2518172956 @default.
• W4312994048 cites W2576309025 @default.
• W4312994048 cites W2746474733 @default.
• W4312994048 cites W2804998325 @default.
• W4312994048 cites W2806000759 @default.
• W4312994048 cites W2889329491 @default.
• W4312994048 cites W2899877258 @default.
• W4312994048 cites W2902070858 @default.
• W4312994048 cites W2962896155 @default.
• W4312994048 cites W2963091184 @default.
• W4312994048 cites W2963539064 @default.
• W4312994048 cites W2963609956 @default.
• W4312994048 cites W2972313557 @default.
• W4312994048 cites W2973108288 @default.
• W4312994048 cites W3015338123 @default.
• W4312994048 cites W3015347659 @default.
• W4312994048 cites W3095158543 @default.
• W4312994048 cites W3095459301 @default.
• W4312994048 cites W3095851005 @default.
• W4312994048 cites W3098557217 @default.
• W4312994048 cites W3099078140 @default.
• W4312994048 cites W3101689408 @default.
• W4312994048 cites W3113687514 @default.
• W4312994048 cites W3117914007 @default.
• W4312994048 cites W3134921434 @default.
• W4312994048 cites W3196702840 @default.
• W4312994048 cites W3198020407 @default.
• W4312994048 cites W4244543785 @default.
• W4312994048 cites W4297841815 @default.
• W4312994048 doi "https://doi.org/10.1109/access.2022.3226350" @default.
• W4312994048 hasPublicationYear "2022" @default.
• W4312994048 type Work @default.
• W4312994048 citedByCount "0" @default.
• W4312994048 crossrefType "journal-article" @default.
• W4312994048 hasAuthorship W4312994048A5007826853 @default.
• W4312994048 hasAuthorship W4312994048A5034095159 @default.
• W4312994048 hasAuthorship W4312994048A5039529498 @default.
• W4312994048 hasAuthorship W4312994048A5055128383 @default.
• W4312994048 hasBestOaLocation W43129940481 @default.
• W4312994048 hasConcept C111472728 @default.
• W4312994048 hasConcept C121332964 @default.
• W4312994048 hasConcept C133892786 @default.
• W4312994048 hasConcept C134537474 @default.
• W4312994048 hasConcept C138885662 @default.
• W4312994048 hasConcept C14999030 @default.
• W4312994048 hasConcept C154945302 @default.
• W4312994048 hasConcept C155635449 @default.
• W4312994048 hasConcept C204321447 @default.
• W4312994048 hasConcept C2775852435 @default.
• W4312994048 hasConcept C28490314 @default.
• W4312994048 hasConcept C41008148 @default.
• W4312994048 hasConcept C60048801 @default.
• W4312994048 hasConcept C61328038 @default.
• W4312994048 hasConcept C62520636 @default.
• W4312994048 hasConcept C91863865 @default.
• W4312994048 hasConceptScore W4312994048C111472728 @default.
• W4312994048 hasConceptScore W4312994048C121332964 @default.
• W4312994048 hasConceptScore W4312994048C133892786 @default.
• W4312994048 hasConceptScore W4312994048C134537474 @default.
• W4312994048 hasConceptScore W4312994048C138885662 @default.
• W4312994048 hasConceptScore W4312994048C14999030 @default.
• W4312994048 hasConceptScore W4312994048C154945302 @default.
• W4312994048 hasConceptScore W4312994048C155635449 @default.
• W4312994048 hasConceptScore W4312994048C204321447 @default.
• W4312994048 hasConceptScore W4312994048C2775852435 @default.
• W4312994048 hasConceptScore W4312994048C28490314 @default.
• W4312994048 hasConceptScore W4312994048C41008148 @default.
• W4312994048 hasConceptScore W4312994048C60048801 @default.
• W4312994048 hasConceptScore W4312994048C61328038 @default.
• W4312994048 hasConceptScore W4312994048C62520636 @default.
• W4312994048 hasConceptScore W4312994048C91863865 @default.
• W4312994048 hasLocation W43129940481 @default.
• W4312994048 hasOpenAccess W4312994048 @default.
• W4312994048 hasPrimaryLocation W43129940481 @default.
• W4312994048 hasRelatedWork W1540787848 @default.
• W4312994048 hasRelatedWork W2120260381 @default.
• W4312994048 hasRelatedWork W2181773877 @default.
• W4312994048 hasRelatedWork W2331981651 @default.
• W4312994048 hasRelatedWork W2394527820 @default.
• W4312994048 hasRelatedWork W2729851813 @default.
• W4312994048 hasRelatedWork W3164843644 @default.

• next