FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3181438018> ?p ?o ?g. }

• W3181438018 abstract "This paper describes a variational auto-encoder based non-autoregressive text-to-speech (VAENAR-TTS) model. The autoregressive TTS (AR-TTS) models based on the sequence-to-sequence architecture can generate high-quality speech, but their sequential decoding process can be time-consuming. Recently, non-autoregressive TTS (NAR-TTS) models have been shown to be more efficient with the parallel decoding process. However, these NAR-TTS models rely on phoneme-level durations to generate a hard alignment between the text and the spectrogram. Obtaining duration labels, either through forced alignment or knowledge distillation, is cumbersome. Furthermore, hard alignment based on phoneme expansion can degrade the naturalness of the synthesized speech. In contrast, the proposed model of VAENAR-TTS is an end-to-end approach that does not require phoneme-level durations. The VAENAR-TTS model does not contain recurrent structures and is completely non-autoregressive in both the training and inference phases. Based on the VAE architecture, the alignment information is encoded in the latent variable, and attention-based soft alignment between the text and the latent variable is used in the decoder to reconstruct the spectrogram. Experiments show that VAENAR-TTS achieves state-of-the-art synthesis quality, while the synthesis speed is comparable with other NAR-TTS models." @default.
• W3181438018 created "2021-07-19" @default.
• W3181438018 creator A5013016841 @default.
• W3181438018 creator A5019458385 @default.
• W3181438018 creator A5025119324 @default.
• W3181438018 creator A5026000663 @default.
• W3181438018 creator A5037109470 @default.
• W3181438018 creator A5048742416 @default.
• W3181438018 creator A5083463839 @default.
• W3181438018 date "2021-07-07" @default.
• W3181438018 modified "2023-10-14" @default.
• W3181438018 title "VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis" @default.
• W3181438018 cites W1665214252 @default.
• W3181438018 cites W1836465849 @default.
• W3181438018 cites W2095705004 @default.
• W3181438018 cites W2102003408 @default.
• W3181438018 cites W2766812927 @default.
• W3181438018 cites W2903739847 @default.
• W3181438018 cites W2963403868 @default.
• W3181438018 cites W2963609956 @default.
• W3181438018 cites W2964121744 @default.
• W3181438018 cites W2964243274 @default.
• W3181438018 cites W2964308564 @default.
• W3181438018 cites W2970730223 @default.
• W3181438018 cites W2970832665 @default.
• W3181438018 cites W3015282541 @default.
• W3181438018 cites W3035083561 @default.
• W3181438018 cites W3098403858 @default.
• W3181438018 cites W3125481789 @default.
• W3181438018 cites W3130016944 @default.
• W3181438018 cites W854541894 @default.
• W3181438018 cites W3098304089 @default.
• W3181438018 doi "https://doi.org/10.48550/arxiv.2107.03298" @default.
• W3181438018 hasPublicationYear "2021" @default.
• W3181438018 type Work @default.
• W3181438018 sameAs 3181438018 @default.
• W3181438018 citedByCount "0" @default.
• W3181438018 crossrefType "posted-content" @default.
• W3181438018 hasAuthorship W3181438018A5013016841 @default.
• W3181438018 hasAuthorship W3181438018A5019458385 @default.
• W3181438018 hasAuthorship W3181438018A5025119324 @default.
• W3181438018 hasAuthorship W3181438018A5026000663 @default.
• W3181438018 hasAuthorship W3181438018A5037109470 @default.
• W3181438018 hasAuthorship W3181438018A5048742416 @default.
• W3181438018 hasAuthorship W3181438018A5083463839 @default.
• W3181438018 hasBestOaLocation W31814380181 @default.
• W3181438018 hasConcept C101738243 @default.
• W3181438018 hasConcept C111919701 @default.
• W3181438018 hasConcept C11413529 @default.
• W3181438018 hasConcept C118505674 @default.
• W3181438018 hasConcept C121332964 @default.
• W3181438018 hasConcept C134537474 @default.
• W3181438018 hasConcept C149782125 @default.
• W3181438018 hasConcept C14999030 @default.
• W3181438018 hasConcept C153180895 @default.
• W3181438018 hasConcept C154945302 @default.
• W3181438018 hasConcept C159877910 @default.
• W3181438018 hasConcept C2776214188 @default.
• W3181438018 hasConcept C2778112365 @default.
• W3181438018 hasConcept C28490314 @default.
• W3181438018 hasConcept C33923547 @default.
• W3181438018 hasConcept C41008148 @default.
• W3181438018 hasConcept C45273575 @default.
• W3181438018 hasConcept C50644808 @default.
• W3181438018 hasConcept C51167844 @default.
• W3181438018 hasConcept C54355233 @default.
• W3181438018 hasConcept C57273362 @default.
• W3181438018 hasConcept C62520636 @default.
• W3181438018 hasConcept C86803240 @default.
• W3181438018 hasConceptScore W3181438018C101738243 @default.
• W3181438018 hasConceptScore W3181438018C111919701 @default.
• W3181438018 hasConceptScore W3181438018C11413529 @default.
• W3181438018 hasConceptScore W3181438018C118505674 @default.
• W3181438018 hasConceptScore W3181438018C121332964 @default.
• W3181438018 hasConceptScore W3181438018C134537474 @default.
• W3181438018 hasConceptScore W3181438018C149782125 @default.
• W3181438018 hasConceptScore W3181438018C14999030 @default.
• W3181438018 hasConceptScore W3181438018C153180895 @default.
• W3181438018 hasConceptScore W3181438018C154945302 @default.
• W3181438018 hasConceptScore W3181438018C159877910 @default.
• W3181438018 hasConceptScore W3181438018C2776214188 @default.
• W3181438018 hasConceptScore W3181438018C2778112365 @default.
• W3181438018 hasConceptScore W3181438018C28490314 @default.
• W3181438018 hasConceptScore W3181438018C33923547 @default.
• W3181438018 hasConceptScore W3181438018C41008148 @default.
• W3181438018 hasConceptScore W3181438018C45273575 @default.
• W3181438018 hasConceptScore W3181438018C50644808 @default.
• W3181438018 hasConceptScore W3181438018C51167844 @default.
• W3181438018 hasConceptScore W3181438018C54355233 @default.
• W3181438018 hasConceptScore W3181438018C57273362 @default.
• W3181438018 hasConceptScore W3181438018C62520636 @default.
• W3181438018 hasConceptScore W3181438018C86803240 @default.
• W3181438018 hasLocation W31814380181 @default.
• W3181438018 hasOpenAccess W3181438018 @default.
• W3181438018 hasPrimaryLocation W31814380181 @default.
• W3181438018 hasRelatedWork W2959758584 @default.
• W3181438018 hasRelatedWork W3090528452 @default.
• W3181438018 hasRelatedWork W3093733783 @default.
• W3181438018 hasRelatedWork W3181438018 @default.
• W3181438018 hasRelatedWork W3195005325 @default.

• next