Matches in SemOpenAlex for { <https://semopenalex.org/work/W2594927458> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2594927458 abstract "Deep Learning has been applied successfully to speech processing problems. In this work we explore its capabilities, focusing concretely in recurrent neural architectures to build a state of the art Text-To-Speech system from scratch. The different steps to make the full TTS system are shown. Also, a post-filtering method to improve the generated speech naturalness is applied and evaluated. The objective results show which architecture fits better our problem, achieving low error rates in term of cepstral distortion, pitch estimation error and voiced/unvoiced classification error. Also, subjective results suggest that the model achieves a state of the art quality in the synthesis, where the post-filtering factor seems to be a key component to get a good level of naturalness. A novel architecture called Multi-Output TTS is also proposed to hold multiple speakers inside the same structure. Some hidden layers are shared by all the speakers, while there is a specific output layer for each speaker. Objective and perceptual experiments prove that this scheme produces much better results in comparison with single speaker models. Moreover, we also tackle the problem of speaker adaptation by adding a new output branch to the model and successfully training it without the need of modifying the base optimized model. This fine tuning method achieves better results than training the new speaker from scratch with its own model. Finally, we also tackle the problem of speaker interpolation by adding a new output layer (alpha-layer) on top of the Multi-Output branches. An identifying code is injected into the layer together with acoustic features of many speakers. Experiments show that the alpha-layer can effectively learn to interpolate the acoustic features between speakers." @default.
- W2594927458 created "2017-03-16" @default.
- W2594927458 creator A5081284433 @default.
- W2594927458 date "2016-06-30" @default.
- W2594927458 modified "2023-09-22" @default.
- W2594927458 title "Deep learning applied to speech synthesis" @default.
- W2594927458 hasPublicationYear "2016" @default.
- W2594927458 type Work @default.
- W2594927458 sameAs 2594927458 @default.
- W2594927458 citedByCount "3" @default.
- W2594927458 countsByYear W25949274582018 @default.
- W2594927458 countsByYear W25949274582019 @default.
- W2594927458 crossrefType "dissertation" @default.
- W2594927458 hasAuthorship W2594927458A5081284433 @default.
- W2594927458 hasConcept C108583219 @default.
- W2594927458 hasConcept C121332964 @default.
- W2594927458 hasConcept C134537474 @default.
- W2594927458 hasConcept C138885662 @default.
- W2594927458 hasConcept C14999030 @default.
- W2594927458 hasConcept C154945302 @default.
- W2594927458 hasConcept C178790620 @default.
- W2594927458 hasConcept C185592680 @default.
- W2594927458 hasConcept C26517878 @default.
- W2594927458 hasConcept C2776401178 @default.
- W2594927458 hasConcept C2779227376 @default.
- W2594927458 hasConcept C28490314 @default.
- W2594927458 hasConcept C38652104 @default.
- W2594927458 hasConcept C41008148 @default.
- W2594927458 hasConcept C41895202 @default.
- W2594927458 hasConcept C62520636 @default.
- W2594927458 hasConceptScore W2594927458C108583219 @default.
- W2594927458 hasConceptScore W2594927458C121332964 @default.
- W2594927458 hasConceptScore W2594927458C134537474 @default.
- W2594927458 hasConceptScore W2594927458C138885662 @default.
- W2594927458 hasConceptScore W2594927458C14999030 @default.
- W2594927458 hasConceptScore W2594927458C154945302 @default.
- W2594927458 hasConceptScore W2594927458C178790620 @default.
- W2594927458 hasConceptScore W2594927458C185592680 @default.
- W2594927458 hasConceptScore W2594927458C26517878 @default.
- W2594927458 hasConceptScore W2594927458C2776401178 @default.
- W2594927458 hasConceptScore W2594927458C2779227376 @default.
- W2594927458 hasConceptScore W2594927458C28490314 @default.
- W2594927458 hasConceptScore W2594927458C38652104 @default.
- W2594927458 hasConceptScore W2594927458C41008148 @default.
- W2594927458 hasConceptScore W2594927458C41895202 @default.
- W2594927458 hasConceptScore W2594927458C62520636 @default.
- W2594927458 hasLocation W25949274581 @default.
- W2594927458 hasOpenAccess W2594927458 @default.
- W2594927458 hasPrimaryLocation W25949274581 @default.
- W2594927458 hasRelatedWork W2403731734 @default.
- W2594927458 hasRelatedWork W2520176975 @default.
- W2594927458 hasRelatedWork W2562274522 @default.
- W2594927458 hasRelatedWork W2777114772 @default.
- W2594927458 hasRelatedWork W2892620417 @default.
- W2594927458 hasRelatedWork W2939771864 @default.
- W2594927458 hasRelatedWork W3005914302 @default.
- W2594927458 hasRelatedWork W3011028252 @default.
- W2594927458 hasRelatedWork W3016048045 @default.
- W2594927458 hasRelatedWork W3022377205 @default.
- W2594927458 hasRelatedWork W3029282897 @default.
- W2594927458 hasRelatedWork W3033194228 @default.
- W2594927458 hasRelatedWork W3093704024 @default.
- W2594927458 hasRelatedWork W3108184206 @default.
- W2594927458 hasRelatedWork W3120557855 @default.
- W2594927458 hasRelatedWork W3163929126 @default.
- W2594927458 hasRelatedWork W3168527213 @default.
- W2594927458 hasRelatedWork W3201363892 @default.
- W2594927458 hasRelatedWork W3211614993 @default.
- W2594927458 hasRelatedWork W32689833 @default.
- W2594927458 isParatext "false" @default.
- W2594927458 isRetracted "false" @default.
- W2594927458 magId "2594927458" @default.
- W2594927458 workType "dissertation" @default.