Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892734764> ?p ?o ?g. }
- W2892734764 abstract "So far, many of the deep learning approaches for voice conversion produce good quality speech by using a large amount of training data. This paper presents a Deep Bidirectional Long Short-Term Memory (DBLSTM) based voice conversion framework that can work with a limited amount of training data. We propose to implement a DBLSTM based average model that is trained with data from many speakers. Then, we propose to perform adaptation with a limited amount of target data. Last but not least, we propose an error reduction network that can improve the voice conversion quality even further. The proposed framework is motivated by three observations. Firstly, DBLSTM can achieve a remarkable voice conversion by considering the long-term dependencies of the speech utterance. Secondly, DBLSTM based average model can be easily adapted with a small amount of data, to achieve a speech that sounds closer to the target. Thirdly, an error reduction network can be trained with a small amount of training data, and can improve the conversion quality effectively. The experiments show that the proposed voice conversion framework is flexible to work with limited training data and outperforms the traditional frameworks in both objective and subjective evaluations." @default.
- W2892734764 created "2018-10-05" @default.
- W2892734764 creator A5001303929 @default.
- W2892734764 creator A5032690182 @default.
- W2892734764 creator A5067273589 @default.
- W2892734764 creator A5071466474 @default.
- W2892734764 creator A5090694009 @default.
- W2892734764 date "2018-11-01" @default.
- W2892734764 modified "2023-09-25" @default.
- W2892734764 title "Error Reduction Network for DBLSTM-based Voice Conversion" @default.
- W2892734764 cites W1509691205 @default.
- W2892734764 cites W1517202054 @default.
- W2892734764 cites W1974745215 @default.
- W2892734764 cites W1977362459 @default.
- W2892734764 cites W2005438552 @default.
- W2892734764 cites W2005708641 @default.
- W2892734764 cites W2009272428 @default.
- W2892734764 cites W2021913835 @default.
- W2892734764 cites W2022125261 @default.
- W2892734764 cites W2049686551 @default.
- W2892734764 cites W2056852181 @default.
- W2892734764 cites W2057609679 @default.
- W2892734764 cites W2064675550 @default.
- W2892734764 cites W2079735306 @default.
- W2892734764 cites W2086796102 @default.
- W2892734764 cites W2107860279 @default.
- W2892734764 cites W2107878631 @default.
- W2892734764 cites W2115055618 @default.
- W2892734764 cites W2120605154 @default.
- W2892734764 cites W2123003832 @default.
- W2892734764 cites W2149940198 @default.
- W2892734764 cites W2169652224 @default.
- W2892734764 cites W2293049663 @default.
- W2892734764 cites W2471933213 @default.
- W2892734764 cites W2563155481 @default.
- W2892734764 cites W2747753032 @default.
- W2892734764 cites W2749262635 @default.
- W2892734764 cites W2785978752 @default.
- W2892734764 doi "https://doi.org/10.23919/apsipa.2018.8659543" @default.
- W2892734764 hasPublicationYear "2018" @default.
- W2892734764 type Work @default.
- W2892734764 sameAs 2892734764 @default.
- W2892734764 citedByCount "14" @default.
- W2892734764 countsByYear W28927347642019 @default.
- W2892734764 countsByYear W28927347642020 @default.
- W2892734764 countsByYear W28927347642021 @default.
- W2892734764 countsByYear W28927347642022 @default.
- W2892734764 countsByYear W28927347642023 @default.
- W2892734764 crossrefType "proceedings-article" @default.
- W2892734764 hasAuthorship W2892734764A5001303929 @default.
- W2892734764 hasAuthorship W2892734764A5032690182 @default.
- W2892734764 hasAuthorship W2892734764A5067273589 @default.
- W2892734764 hasAuthorship W2892734764A5071466474 @default.
- W2892734764 hasAuthorship W2892734764A5090694009 @default.
- W2892734764 hasBestOaLocation W28927347642 @default.
- W2892734764 hasConcept C111335779 @default.
- W2892734764 hasConcept C111472728 @default.
- W2892734764 hasConcept C121332964 @default.
- W2892734764 hasConcept C138885662 @default.
- W2892734764 hasConcept C154945302 @default.
- W2892734764 hasConcept C2524010 @default.
- W2892734764 hasConcept C2775852435 @default.
- W2892734764 hasConcept C2779530757 @default.
- W2892734764 hasConcept C28490314 @default.
- W2892734764 hasConcept C33923547 @default.
- W2892734764 hasConcept C41008148 @default.
- W2892734764 hasConcept C51632099 @default.
- W2892734764 hasConcept C61797465 @default.
- W2892734764 hasConcept C62520636 @default.
- W2892734764 hasConceptScore W2892734764C111335779 @default.
- W2892734764 hasConceptScore W2892734764C111472728 @default.
- W2892734764 hasConceptScore W2892734764C121332964 @default.
- W2892734764 hasConceptScore W2892734764C138885662 @default.
- W2892734764 hasConceptScore W2892734764C154945302 @default.
- W2892734764 hasConceptScore W2892734764C2524010 @default.
- W2892734764 hasConceptScore W2892734764C2775852435 @default.
- W2892734764 hasConceptScore W2892734764C2779530757 @default.
- W2892734764 hasConceptScore W2892734764C28490314 @default.
- W2892734764 hasConceptScore W2892734764C33923547 @default.
- W2892734764 hasConceptScore W2892734764C41008148 @default.
- W2892734764 hasConceptScore W2892734764C51632099 @default.
- W2892734764 hasConceptScore W2892734764C61797465 @default.
- W2892734764 hasConceptScore W2892734764C62520636 @default.
- W2892734764 hasLocation W28927347641 @default.
- W2892734764 hasLocation W28927347642 @default.
- W2892734764 hasOpenAccess W2892734764 @default.
- W2892734764 hasPrimaryLocation W28927347641 @default.
- W2892734764 hasRelatedWork W1596769518 @default.
- W2892734764 hasRelatedWork W1964230095 @default.
- W2892734764 hasRelatedWork W2101293477 @default.
- W2892734764 hasRelatedWork W2153327798 @default.
- W2892734764 hasRelatedWork W2336335760 @default.
- W2892734764 hasRelatedWork W2886693075 @default.
- W2892734764 hasRelatedWork W3011644728 @default.
- W2892734764 hasRelatedWork W3092864024 @default.
- W2892734764 hasRelatedWork W3198503472 @default.
- W2892734764 hasRelatedWork W4307784074 @default.
- W2892734764 isParatext "false" @default.
- W2892734764 isRetracted "false" @default.
- W2892734764 magId "2892734764" @default.