Matches in SemOpenAlex for { <https://semopenalex.org/work/W2800962324> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2800962324 abstract "We describe a new application of deep-learning-based speech synthesis, namely multilingual speech synthesis for generating controllable foreign accent. Specifically, we train a DBLSTM-based acoustic model on non-accented multilingual speech recordings from a speaker native in several languages. By copying durations and pitch contours from a pre-recorded utterance of the desired prompt, natural prosody is achieved. We call this paradigm “cyborg speech” as it combines human and machine speech parameters. Segmentally accented speech is produced by interpolating specific quinphone linguistic features towards phones from the other language that represent non-native mispronunciations. Experiments on synthetic American-English-accented Japanese speech show that subjective synthesis quality matches monolingual synthesis, that natural pitch is maintained, and that naturalistic phone substitutions generate output that is perceived as having an American foreign accent, even though only non-accented training data was used." @default.
- W2800962324 created "2018-05-17" @default.
- W2800962324 creator A5006822602 @default.
- W2800962324 creator A5007639385 @default.
- W2800962324 creator A5019530089 @default.
- W2800962324 creator A5082512344 @default.
- W2800962324 creator A5091432739 @default.
- W2800962324 date "2018-04-01" @default.
- W2800962324 modified "2023-09-27" @default.
- W2800962324 title "Cyborg Speech: Deep Multilingual Speech Synthesis for Generating Segmental Foreign Accent with Natural Prosody" @default.
- W2800962324 cites W1999885698 @default.
- W2800962324 cites W2002389722 @default.
- W2800962324 cites W2066452495 @default.
- W2800962324 cites W2089324793 @default.
- W2800962324 cites W2102157173 @default.
- W2800962324 cites W2103651905 @default.
- W2800962324 cites W2131825398 @default.
- W2800962324 cites W2141720691 @default.
- W2800962324 cites W2157429465 @default.
- W2800962324 cites W2168943479 @default.
- W2800962324 cites W2402539796 @default.
- W2800962324 cites W2494654097 @default.
- W2800962324 doi "https://doi.org/10.1109/icassp.2018.8462470" @default.
- W2800962324 hasPublicationYear "2018" @default.
- W2800962324 type Work @default.
- W2800962324 sameAs 2800962324 @default.
- W2800962324 citedByCount "3" @default.
- W2800962324 countsByYear W28009623242019 @default.
- W2800962324 countsByYear W28009623242020 @default.
- W2800962324 crossrefType "proceedings-article" @default.
- W2800962324 hasAuthorship W2800962324A5006822602 @default.
- W2800962324 hasAuthorship W2800962324A5007639385 @default.
- W2800962324 hasAuthorship W2800962324A5019530089 @default.
- W2800962324 hasAuthorship W2800962324A5082512344 @default.
- W2800962324 hasAuthorship W2800962324A5091432739 @default.
- W2800962324 hasBestOaLocation W28009623242 @default.
- W2800962324 hasConcept C138885662 @default.
- W2800962324 hasConcept C14999030 @default.
- W2800962324 hasConcept C154945302 @default.
- W2800962324 hasConcept C166957645 @default.
- W2800962324 hasConcept C204321447 @default.
- W2800962324 hasConcept C2775852435 @default.
- W2800962324 hasConcept C2776608160 @default.
- W2800962324 hasConcept C2776756274 @default.
- W2800962324 hasConcept C2777672088 @default.
- W2800962324 hasConcept C2778707766 @default.
- W2800962324 hasConcept C28490314 @default.
- W2800962324 hasConcept C41008148 @default.
- W2800962324 hasConcept C41895202 @default.
- W2800962324 hasConcept C542774811 @default.
- W2800962324 hasConcept C95457728 @default.
- W2800962324 hasConceptScore W2800962324C138885662 @default.
- W2800962324 hasConceptScore W2800962324C14999030 @default.
- W2800962324 hasConceptScore W2800962324C154945302 @default.
- W2800962324 hasConceptScore W2800962324C166957645 @default.
- W2800962324 hasConceptScore W2800962324C204321447 @default.
- W2800962324 hasConceptScore W2800962324C2775852435 @default.
- W2800962324 hasConceptScore W2800962324C2776608160 @default.
- W2800962324 hasConceptScore W2800962324C2776756274 @default.
- W2800962324 hasConceptScore W2800962324C2777672088 @default.
- W2800962324 hasConceptScore W2800962324C2778707766 @default.
- W2800962324 hasConceptScore W2800962324C28490314 @default.
- W2800962324 hasConceptScore W2800962324C41008148 @default.
- W2800962324 hasConceptScore W2800962324C41895202 @default.
- W2800962324 hasConceptScore W2800962324C542774811 @default.
- W2800962324 hasConceptScore W2800962324C95457728 @default.
- W2800962324 hasLocation W28009623241 @default.
- W2800962324 hasLocation W28009623242 @default.
- W2800962324 hasOpenAccess W2800962324 @default.
- W2800962324 hasPrimaryLocation W28009623241 @default.
- W2800962324 hasRelatedWork W125088710 @default.
- W2800962324 hasRelatedWork W156336793 @default.
- W2800962324 hasRelatedWork W1871400908 @default.
- W2800962324 hasRelatedWork W2068376207 @default.
- W2800962324 hasRelatedWork W2084581906 @default.
- W2800962324 hasRelatedWork W2154644810 @default.
- W2800962324 hasRelatedWork W2800962324 @default.
- W2800962324 hasRelatedWork W2954635359 @default.
- W2800962324 hasRelatedWork W4206003764 @default.
- W2800962324 hasRelatedWork W4319781852 @default.
- W2800962324 isParatext "false" @default.
- W2800962324 isRetracted "false" @default.
- W2800962324 magId "2800962324" @default.
- W2800962324 workType "article" @default.