Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200187816> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3200187816 abstract "Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the input text using a generic text-to-speech (TTS) engine and then transform the voice to the desired voice using voice conversion (VC). A major problem of this framework is that VC is a challenging problem which usually needs a moderate amount of parallel training data to work satisfactorily. In this paper, we propose a one-stage context-aware framework to generate natural and coherent target speech without any training data of the target speaker. In particular, we manage to perform accurate zero-shot duration prediction for the inserted text. The predicted duration is used to regulate both text embedding and speech embedding. Then, based on the aligned cross-modality input, we directly generate the mel-spectrogram of the edited speech with a transformer-based decoder. Subjective listening tests show that despite the lack of training data for the speaker, our method has achieved satisfactory results. It outperforms a recent zero-shot TTS engine by a large margin." @default.
- W3200187816 created "2021-09-27" @default.
- W3200187816 creator A5004867590 @default.
- W3200187816 creator A5005976848 @default.
- W3200187816 creator A5034383847 @default.
- W3200187816 creator A5044136249 @default.
- W3200187816 creator A5049963367 @default.
- W3200187816 creator A5079531245 @default.
- W3200187816 date "2021-09-12" @default.
- W3200187816 modified "2023-10-14" @default.
- W3200187816 title "Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration" @default.
- W3200187816 cites W1522301498 @default.
- W3200187816 cites W2120847449 @default.
- W3200187816 cites W2402356521 @default.
- W3200187816 cites W2608207374 @default.
- W3200187816 cites W2626778328 @default.
- W3200187816 cites W2737697117 @default.
- W3200187816 cites W2747874407 @default.
- W3200187816 cites W2808706139 @default.
- W3200187816 cites W2903739847 @default.
- W3200187816 cites W2946200149 @default.
- W3200187816 cites W2960274051 @default.
- W3200187816 cites W2964243274 @default.
- W3200187816 cites W3015676952 @default.
- W3200187816 cites W3020570669 @default.
- W3200187816 cites W3130821015 @default.
- W3200187816 doi "https://doi.org/10.48550/arxiv.2109.05426" @default.
- W3200187816 hasPublicationYear "2021" @default.
- W3200187816 type Work @default.
- W3200187816 sameAs 3200187816 @default.
- W3200187816 citedByCount "0" @default.
- W3200187816 crossrefType "posted-content" @default.
- W3200187816 hasAuthorship W3200187816A5004867590 @default.
- W3200187816 hasAuthorship W3200187816A5005976848 @default.
- W3200187816 hasAuthorship W3200187816A5034383847 @default.
- W3200187816 hasAuthorship W3200187816A5044136249 @default.
- W3200187816 hasAuthorship W3200187816A5049963367 @default.
- W3200187816 hasAuthorship W3200187816A5079531245 @default.
- W3200187816 hasBestOaLocation W32001878161 @default.
- W3200187816 hasConcept C121332964 @default.
- W3200187816 hasConcept C14999030 @default.
- W3200187816 hasConcept C151730666 @default.
- W3200187816 hasConcept C154945302 @default.
- W3200187816 hasConcept C165801399 @default.
- W3200187816 hasConcept C204321447 @default.
- W3200187816 hasConcept C2779343474 @default.
- W3200187816 hasConcept C28490314 @default.
- W3200187816 hasConcept C41008148 @default.
- W3200187816 hasConcept C41608201 @default.
- W3200187816 hasConcept C45273575 @default.
- W3200187816 hasConcept C62520636 @default.
- W3200187816 hasConcept C66322947 @default.
- W3200187816 hasConcept C86803240 @default.
- W3200187816 hasConceptScore W3200187816C121332964 @default.
- W3200187816 hasConceptScore W3200187816C14999030 @default.
- W3200187816 hasConceptScore W3200187816C151730666 @default.
- W3200187816 hasConceptScore W3200187816C154945302 @default.
- W3200187816 hasConceptScore W3200187816C165801399 @default.
- W3200187816 hasConceptScore W3200187816C204321447 @default.
- W3200187816 hasConceptScore W3200187816C2779343474 @default.
- W3200187816 hasConceptScore W3200187816C28490314 @default.
- W3200187816 hasConceptScore W3200187816C41008148 @default.
- W3200187816 hasConceptScore W3200187816C41608201 @default.
- W3200187816 hasConceptScore W3200187816C45273575 @default.
- W3200187816 hasConceptScore W3200187816C62520636 @default.
- W3200187816 hasConceptScore W3200187816C66322947 @default.
- W3200187816 hasConceptScore W3200187816C86803240 @default.
- W3200187816 hasLocation W32001878161 @default.
- W3200187816 hasOpenAccess W3200187816 @default.
- W3200187816 hasPrimaryLocation W32001878161 @default.
- W3200187816 hasRelatedWork W2921059071 @default.
- W3200187816 hasRelatedWork W2946200149 @default.
- W3200187816 hasRelatedWork W2970730223 @default.
- W3200187816 hasRelatedWork W3107474891 @default.
- W3200187816 hasRelatedWork W3120578578 @default.
- W3200187816 hasRelatedWork W3127598333 @default.
- W3200187816 hasRelatedWork W3203164699 @default.
- W3200187816 hasRelatedWork W4290074601 @default.
- W3200187816 hasRelatedWork W4310471687 @default.
- W3200187816 hasRelatedWork W4312706341 @default.
- W3200187816 isParatext "false" @default.
- W3200187816 isRetracted "false" @default.
- W3200187816 magId "3200187816" @default.
- W3200187816 workType "article" @default.