Matches in SemOpenAlex for { <https://semopenalex.org/work/W4372260216> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4372260216 abstract "Deep learning based text-to-speech (TTS) systems have been evolving rapidly with advances in model architectures, training methodologies, and generalization across speakers and languages. However, these advances have not been thoroughly investigated for Indian language speech synthesis. Such investigation is computationally expensive given the number and diversity of Indian languages, relatively lower resource availability, and the diverse set of advances in neural TTS that remain untested. In this paper, we evaluate the choice of acoustic models, vocoders, supplementary loss functions, training schedules, and speaker and language diversity for Dravidian and Indo-Aryan languages. Based on this, we identify monolingual models with FastPitch and HiFi-GAN V1, trained jointly on male and female speakers to perform the best. With this setup, we train and evaluate TTS models for 13 languages and find our models to significantly improve upon existing models in all languages as measured by mean opinion scores. We open-source all models on the Bhashini platform." @default.
- W4372260216 created "2023-05-07" @default.
- W4372260216 creator A5019249168 @default.
- W4372260216 creator A5024510660 @default.
- W4372260216 creator A5048139334 @default.
- W4372260216 creator A5050036814 @default.
- W4372260216 creator A5059676452 @default.
- W4372260216 date "2023-06-04" @default.
- W4372260216 modified "2023-09-27" @default.
- W4372260216 title "Towards Building Text-to-Speech Systems for the Next Billion Users" @default.
- W4372260216 cites W2107860279 @default.
- W4372260216 cites W2144994235 @default.
- W4372260216 cites W2471520273 @default.
- W4372260216 cites W2510374792 @default.
- W4372260216 cites W2962788625 @default.
- W4372260216 cites W2963300588 @default.
- W4372260216 cites W2964243274 @default.
- W4372260216 cites W2973034126 @default.
- W4372260216 cites W3095877226 @default.
- W4372260216 cites W3096408984 @default.
- W4372260216 cites W3099919888 @default.
- W4372260216 cites W3144035034 @default.
- W4372260216 cites W3196001064 @default.
- W4372260216 cites W3196667132 @default.
- W4372260216 cites W3198213150 @default.
- W4372260216 cites W3208643357 @default.
- W4372260216 cites W3213618310 @default.
- W4372260216 cites W4226332109 @default.
- W4372260216 doi "https://doi.org/10.1109/icassp49357.2023.10096069" @default.
- W4372260216 hasPublicationYear "2023" @default.
- W4372260216 type Work @default.
- W4372260216 citedByCount "0" @default.
- W4372260216 crossrefType "proceedings-article" @default.
- W4372260216 hasAuthorship W4372260216A5019249168 @default.
- W4372260216 hasAuthorship W4372260216A5024510660 @default.
- W4372260216 hasAuthorship W4372260216A5048139334 @default.
- W4372260216 hasAuthorship W4372260216A5050036814 @default.
- W4372260216 hasAuthorship W4372260216A5059676452 @default.
- W4372260216 hasBestOaLocation W43722602161 @default.
- W4372260216 hasConcept C127413603 @default.
- W4372260216 hasConcept C134306372 @default.
- W4372260216 hasConcept C137293760 @default.
- W4372260216 hasConcept C138885662 @default.
- W4372260216 hasConcept C144024400 @default.
- W4372260216 hasConcept C14999030 @default.
- W4372260216 hasConcept C154945302 @default.
- W4372260216 hasConcept C176217482 @default.
- W4372260216 hasConcept C177148314 @default.
- W4372260216 hasConcept C177264268 @default.
- W4372260216 hasConcept C19165224 @default.
- W4372260216 hasConcept C199360897 @default.
- W4372260216 hasConcept C204321447 @default.
- W4372260216 hasConcept C21547014 @default.
- W4372260216 hasConcept C2777601683 @default.
- W4372260216 hasConcept C2781202465 @default.
- W4372260216 hasConcept C2781316041 @default.
- W4372260216 hasConcept C28490314 @default.
- W4372260216 hasConcept C33923547 @default.
- W4372260216 hasConcept C41008148 @default.
- W4372260216 hasConcept C41895202 @default.
- W4372260216 hasConcept C62897895 @default.
- W4372260216 hasConceptScore W4372260216C127413603 @default.
- W4372260216 hasConceptScore W4372260216C134306372 @default.
- W4372260216 hasConceptScore W4372260216C137293760 @default.
- W4372260216 hasConceptScore W4372260216C138885662 @default.
- W4372260216 hasConceptScore W4372260216C144024400 @default.
- W4372260216 hasConceptScore W4372260216C14999030 @default.
- W4372260216 hasConceptScore W4372260216C154945302 @default.
- W4372260216 hasConceptScore W4372260216C176217482 @default.
- W4372260216 hasConceptScore W4372260216C177148314 @default.
- W4372260216 hasConceptScore W4372260216C177264268 @default.
- W4372260216 hasConceptScore W4372260216C19165224 @default.
- W4372260216 hasConceptScore W4372260216C199360897 @default.
- W4372260216 hasConceptScore W4372260216C204321447 @default.
- W4372260216 hasConceptScore W4372260216C21547014 @default.
- W4372260216 hasConceptScore W4372260216C2777601683 @default.
- W4372260216 hasConceptScore W4372260216C2781202465 @default.
- W4372260216 hasConceptScore W4372260216C2781316041 @default.
- W4372260216 hasConceptScore W4372260216C28490314 @default.
- W4372260216 hasConceptScore W4372260216C33923547 @default.
- W4372260216 hasConceptScore W4372260216C41008148 @default.
- W4372260216 hasConceptScore W4372260216C41895202 @default.
- W4372260216 hasConceptScore W4372260216C62897895 @default.
- W4372260216 hasLocation W43722602161 @default.
- W4372260216 hasLocation W43722602162 @default.
- W4372260216 hasOpenAccess W4372260216 @default.
- W4372260216 hasPrimaryLocation W43722602161 @default.
- W4372260216 hasRelatedWork W2101569175 @default.
- W4372260216 hasRelatedWork W2151664070 @default.
- W4372260216 hasRelatedWork W2359001871 @default.
- W4372260216 hasRelatedWork W2963879839 @default.
- W4372260216 hasRelatedWork W2968379855 @default.
- W4372260216 hasRelatedWork W3007264682 @default.
- W4372260216 hasRelatedWork W3024752295 @default.
- W4372260216 hasRelatedWork W3127598333 @default.
- W4372260216 hasRelatedWork W4205278983 @default.
- W4372260216 hasRelatedWork W4297293660 @default.
- W4372260216 isParatext "false" @default.
- W4372260216 isRetracted "false" @default.
- W4372260216 workType "article" @default.