Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290742564> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4290742564 abstract "End-to-end text-to-speech synthesis systems achieved immense success in recent times, with improved naturalness and intelligibility. However, the end-to-end models, which primarily depend on the attention-based alignment, do not offer an explicit provision to modify/incorporate the desired prosody while synthesizing the signal. Moreover, the state-of-the-art end-to-end systems use autoregressive models for synthesis, making the prediction sequential. Hence, the inference time and the computational complexity are quite high. This paper proposes Prosody-TTS, an end-to-end speech synthesis model that combines the advantages of statistical parametric models and end-to-end neural network models. It also has a provision to modify or incorporate the desired prosody by controlling the fundamental frequency (f0) and the phone duration. Generating speech samples with appropriate prosody and rhythm helps in improving the naturalness of the synthesized speech. We explicitly model the duration of the phoneme and the f0 to have control over them during the synthesis. The model is trained in an end-to-end fashion to directly generate the speech waveform from the input text, which in turn depends on the auxiliary subtasks of predicting the phoneme duration, f0, and mel spectrogram. Experiments on the Telugu language data of the IndicTTS database show that the proposed Prosody-TTS model achieves state-of-the-art performance with a mean opinion score of 4.08, with a very low inference time." @default.
- W4290742564 created "2022-08-09" @default.
- W4290742564 creator A5065642629 @default.
- W4290742564 creator A5067617924 @default.
- W4290742564 date "2021-10-06" @default.
- W4290742564 modified "2023-10-17" @default.
- W4290742564 title "Prosody-TTS: An end-to-end speech synthesis system with prosody control" @default.
- W4290742564 doi "https://doi.org/10.48550/arxiv.2110.02854" @default.
- W4290742564 hasPublicationYear "2021" @default.
- W4290742564 type Work @default.
- W4290742564 citedByCount "0" @default.
- W4290742564 crossrefType "posted-content" @default.
- W4290742564 hasAuthorship W4290742564A5065642629 @default.
- W4290742564 hasAuthorship W4290742564A5067617924 @default.
- W4290742564 hasBestOaLocation W42907425641 @default.
- W4290742564 hasConcept C105795698 @default.
- W4290742564 hasConcept C111472728 @default.
- W4290742564 hasConcept C112758219 @default.
- W4290742564 hasConcept C117251300 @default.
- W4290742564 hasConcept C121332964 @default.
- W4290742564 hasConcept C124952713 @default.
- W4290742564 hasConcept C127413603 @default.
- W4290742564 hasConcept C134537474 @default.
- W4290742564 hasConcept C138885662 @default.
- W4290742564 hasConcept C142362112 @default.
- W4290742564 hasConcept C14999030 @default.
- W4290742564 hasConcept C154945302 @default.
- W4290742564 hasConcept C176217482 @default.
- W4290742564 hasConcept C21547014 @default.
- W4290742564 hasConcept C2776214188 @default.
- W4290742564 hasConcept C28490314 @default.
- W4290742564 hasConcept C33923547 @default.
- W4290742564 hasConcept C41008148 @default.
- W4290742564 hasConcept C45273575 @default.
- W4290742564 hasConcept C542774811 @default.
- W4290742564 hasConcept C60048801 @default.
- W4290742564 hasConcept C62520636 @default.
- W4290742564 hasConcept C62897895 @default.
- W4290742564 hasConcept C74296488 @default.
- W4290742564 hasConceptScore W4290742564C105795698 @default.
- W4290742564 hasConceptScore W4290742564C111472728 @default.
- W4290742564 hasConceptScore W4290742564C112758219 @default.
- W4290742564 hasConceptScore W4290742564C117251300 @default.
- W4290742564 hasConceptScore W4290742564C121332964 @default.
- W4290742564 hasConceptScore W4290742564C124952713 @default.
- W4290742564 hasConceptScore W4290742564C127413603 @default.
- W4290742564 hasConceptScore W4290742564C134537474 @default.
- W4290742564 hasConceptScore W4290742564C138885662 @default.
- W4290742564 hasConceptScore W4290742564C142362112 @default.
- W4290742564 hasConceptScore W4290742564C14999030 @default.
- W4290742564 hasConceptScore W4290742564C154945302 @default.
- W4290742564 hasConceptScore W4290742564C176217482 @default.
- W4290742564 hasConceptScore W4290742564C21547014 @default.
- W4290742564 hasConceptScore W4290742564C2776214188 @default.
- W4290742564 hasConceptScore W4290742564C28490314 @default.
- W4290742564 hasConceptScore W4290742564C33923547 @default.
- W4290742564 hasConceptScore W4290742564C41008148 @default.
- W4290742564 hasConceptScore W4290742564C45273575 @default.
- W4290742564 hasConceptScore W4290742564C542774811 @default.
- W4290742564 hasConceptScore W4290742564C60048801 @default.
- W4290742564 hasConceptScore W4290742564C62520636 @default.
- W4290742564 hasConceptScore W4290742564C62897895 @default.
- W4290742564 hasConceptScore W4290742564C74296488 @default.
- W4290742564 hasLocation W42907425641 @default.
- W4290742564 hasOpenAccess W4290742564 @default.
- W4290742564 hasPrimaryLocation W42907425641 @default.
- W4290742564 hasRelatedWork W2061706163 @default.
- W4290742564 hasRelatedWork W2067665617 @default.
- W4290742564 hasRelatedWork W2133918396 @default.
- W4290742564 hasRelatedWork W2358167086 @default.
- W4290742564 hasRelatedWork W2395782420 @default.
- W4290742564 hasRelatedWork W2928664166 @default.
- W4290742564 hasRelatedWork W3160844600 @default.
- W4290742564 hasRelatedWork W3203313352 @default.
- W4290742564 hasRelatedWork W3211165121 @default.
- W4290742564 hasRelatedWork W4225694871 @default.
- W4290742564 isParatext "false" @default.
- W4290742564 isRetracted "false" @default.
- W4290742564 workType "article" @default.