Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287067469> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4287067469 abstract "For articulatory-to-acoustic mapping, typically only limited parallel training data is available, making it impossible to apply fully end-to-end solutions like Tacotron2. In this paper, we experimented with transfer learning and adaptation of a Tacotron2 text-to-speech model to improve the final synthesis quality of ultrasound-based articulatory-to-acoustic mapping with a limited database. We use a multi-speaker pre-trained Tacotron2 TTS model and a pre-trained WaveGlow neural vocoder. The articulatory-to-acoustic conversion contains three steps: 1) from a sequence of ultrasound tongue image recordings, a 3D convolutional neural network predicts the inputs of the pre-trained Tacotron2 model, 2) the Tacotron2 model converts this intermediate representation to an 80-dimensional mel-spectrogram, and 3) the WaveGlow model is applied for final inference. This generated speech contains the timing of the original articulatory data from the ultrasound recording, but the F0 contour and the spectral information is predicted by the Tacotron2 model. The F0 values are independent of the original ultrasound images, but represent the target speaker, as they are inferred from the pre-trained Tacotron2 model. In our experiments, we demonstrated that the synthesized speech quality is more natural with the proposed solutions than with our earlier model." @default.
- W4287067469 created "2022-07-25" @default.
- W4287067469 creator A5016031960 @default.
- W4287067469 creator A5026493983 @default.
- W4287067469 creator A5027276858 @default.
- W4287067469 creator A5031237235 @default.
- W4287067469 creator A5069988513 @default.
- W4287067469 creator A5085147054 @default.
- W4287067469 creator A5088559776 @default.
- W4287067469 date "2021-07-26" @default.
- W4287067469 modified "2023-09-28" @default.
- W4287067469 title "Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging" @default.
- W4287067469 doi "https://doi.org/10.48550/arxiv.2107.12051" @default.
- W4287067469 hasPublicationYear "2021" @default.
- W4287067469 type Work @default.
- W4287067469 citedByCount "0" @default.
- W4287067469 crossrefType "posted-content" @default.
- W4287067469 hasAuthorship W4287067469A5016031960 @default.
- W4287067469 hasAuthorship W4287067469A5026493983 @default.
- W4287067469 hasAuthorship W4287067469A5027276858 @default.
- W4287067469 hasAuthorship W4287067469A5031237235 @default.
- W4287067469 hasAuthorship W4287067469A5069988513 @default.
- W4287067469 hasAuthorship W4287067469A5085147054 @default.
- W4287067469 hasAuthorship W4287067469A5088559776 @default.
- W4287067469 hasBestOaLocation W42870674691 @default.
- W4287067469 hasConcept C120665830 @default.
- W4287067469 hasConcept C121332964 @default.
- W4287067469 hasConcept C139807058 @default.
- W4287067469 hasConcept C14999030 @default.
- W4287067469 hasConcept C153180895 @default.
- W4287067469 hasConcept C154945302 @default.
- W4287067469 hasConcept C17744445 @default.
- W4287067469 hasConcept C199539241 @default.
- W4287067469 hasConcept C2776214188 @default.
- W4287067469 hasConcept C2776359362 @default.
- W4287067469 hasConcept C28490314 @default.
- W4287067469 hasConcept C41008148 @default.
- W4287067469 hasConcept C45273575 @default.
- W4287067469 hasConcept C50644808 @default.
- W4287067469 hasConcept C81363708 @default.
- W4287067469 hasConcept C94625758 @default.
- W4287067469 hasConceptScore W4287067469C120665830 @default.
- W4287067469 hasConceptScore W4287067469C121332964 @default.
- W4287067469 hasConceptScore W4287067469C139807058 @default.
- W4287067469 hasConceptScore W4287067469C14999030 @default.
- W4287067469 hasConceptScore W4287067469C153180895 @default.
- W4287067469 hasConceptScore W4287067469C154945302 @default.
- W4287067469 hasConceptScore W4287067469C17744445 @default.
- W4287067469 hasConceptScore W4287067469C199539241 @default.
- W4287067469 hasConceptScore W4287067469C2776214188 @default.
- W4287067469 hasConceptScore W4287067469C2776359362 @default.
- W4287067469 hasConceptScore W4287067469C28490314 @default.
- W4287067469 hasConceptScore W4287067469C41008148 @default.
- W4287067469 hasConceptScore W4287067469C45273575 @default.
- W4287067469 hasConceptScore W4287067469C50644808 @default.
- W4287067469 hasConceptScore W4287067469C81363708 @default.
- W4287067469 hasConceptScore W4287067469C94625758 @default.
- W4287067469 hasLocation W42870674691 @default.
- W4287067469 hasOpenAccess W4287067469 @default.
- W4287067469 hasPrimaryLocation W42870674691 @default.
- W4287067469 hasRelatedWork W2175746458 @default.
- W4287067469 hasRelatedWork W2406522397 @default.
- W4287067469 hasRelatedWork W2613736958 @default.
- W4287067469 hasRelatedWork W2732542196 @default.
- W4287067469 hasRelatedWork W2936488316 @default.
- W4287067469 hasRelatedWork W3004378172 @default.
- W4287067469 hasRelatedWork W3091785813 @default.
- W4287067469 hasRelatedWork W3093612317 @default.
- W4287067469 hasRelatedWork W3207455498 @default.
- W4287067469 hasRelatedWork W4214739189 @default.
- W4287067469 isParatext "false" @default.
- W4287067469 isRetracted "false" @default.
- W4287067469 workType "article" @default.