Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319862245> ?p ?o ?g. }
- W4319862245 abstract "Denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs) are popular generative models for neural vocoders. The DDPMs and GANs can be characterized by the iterative denoising framework and adversarial training, respectively. This study proposes a fast and high-quality neural vocoder called WaveFit, which integrates the essence of GANs into a DDPM-like iterative framework based on fixed-point iteration. WaveFit iteratively denoises an input signal, and trains a deep neural network (DNN) for minimizing an adversarial loss calculated from intermediate outputs at all iterations. Subjective (side-by-side) listening tests showed no statistically significant differences in naturalness between human natural speech and those synthesized by WaveFit with five iterations. Furthermore, the inference speed of WaveFit was more than 240 times faster than WaveRNN. Audio demos are available at google.github.io/df-conformer/wavefit/." @default.
- W4319862245 created "2023-02-11" @default.
- W4319862245 creator A5003420204 @default.
- W4319862245 creator A5015534419 @default.
- W4319862245 creator A5034837951 @default.
- W4319862245 creator A5059692696 @default.
- W4319862245 date "2023-01-09" @default.
- W4319862245 modified "2023-10-01" @default.
- W4319862245 title "Wavefit: an Iterative and Non-Autoregressive Neural Vocoder Based on Fixed-Point Iteration" @default.
- W4319862245 cites W205960364 @default.
- W4319862245 cites W2111395440 @default.
- W4319862245 cites W2749651610 @default.
- W4319862245 cites W2775336875 @default.
- W4319862245 cites W2911317657 @default.
- W4319862245 cites W2962911378 @default.
- W4319862245 cites W2963091184 @default.
- W4319862245 cites W2963300588 @default.
- W4319862245 cites W2964215687 @default.
- W4319862245 cites W2964243274 @default.
- W4319862245 cites W2972359262 @default.
- W4319862245 cites W2972495969 @default.
- W4319862245 cites W2998498479 @default.
- W4319862245 cites W3015338123 @default.
- W4319862245 cites W3047002475 @default.
- W4319862245 cites W3095095816 @default.
- W4319862245 cites W3096159803 @default.
- W4319862245 cites W3096709315 @default.
- W4319862245 cites W3098557217 @default.
- W4319862245 cites W3144035034 @default.
- W4319862245 cites W3162075194 @default.
- W4319862245 cites W3180374548 @default.
- W4319862245 cites W3194208020 @default.
- W4319862245 cites W3197273793 @default.
- W4319862245 cites W3197324626 @default.
- W4319862245 cites W3198234802 @default.
- W4319862245 cites W3200625292 @default.
- W4319862245 cites W3215615641 @default.
- W4319862245 cites W4200483526 @default.
- W4319862245 cites W4221152438 @default.
- W4319862245 cites W4221161734 @default.
- W4319862245 cites W4224931676 @default.
- W4319862245 cites W4225566824 @default.
- W4319862245 cites W4244393449 @default.
- W4319862245 cites W4287889585 @default.
- W4319862245 doi "https://doi.org/10.1109/slt54892.2023.10022496" @default.
- W4319862245 hasPublicationYear "2023" @default.
- W4319862245 type Work @default.
- W4319862245 citedByCount "1" @default.
- W4319862245 countsByYear W43198622452023 @default.
- W4319862245 crossrefType "proceedings-article" @default.
- W4319862245 hasAuthorship W4319862245A5003420204 @default.
- W4319862245 hasAuthorship W4319862245A5015534419 @default.
- W4319862245 hasAuthorship W4319862245A5034837951 @default.
- W4319862245 hasAuthorship W4319862245A5059692696 @default.
- W4319862245 hasBestOaLocation W43198622452 @default.
- W4319862245 hasConcept C11413529 @default.
- W4319862245 hasConcept C121332964 @default.
- W4319862245 hasConcept C134306372 @default.
- W4319862245 hasConcept C134537474 @default.
- W4319862245 hasConcept C149782125 @default.
- W4319862245 hasConcept C154945302 @default.
- W4319862245 hasConcept C159694833 @default.
- W4319862245 hasConcept C159877910 @default.
- W4319862245 hasConcept C2776214188 @default.
- W4319862245 hasConcept C28490314 @default.
- W4319862245 hasConcept C33923547 @default.
- W4319862245 hasConcept C41008148 @default.
- W4319862245 hasConcept C50644808 @default.
- W4319862245 hasConcept C61445026 @default.
- W4319862245 hasConcept C62520636 @default.
- W4319862245 hasConceptScore W4319862245C11413529 @default.
- W4319862245 hasConceptScore W4319862245C121332964 @default.
- W4319862245 hasConceptScore W4319862245C134306372 @default.
- W4319862245 hasConceptScore W4319862245C134537474 @default.
- W4319862245 hasConceptScore W4319862245C149782125 @default.
- W4319862245 hasConceptScore W4319862245C154945302 @default.
- W4319862245 hasConceptScore W4319862245C159694833 @default.
- W4319862245 hasConceptScore W4319862245C159877910 @default.
- W4319862245 hasConceptScore W4319862245C2776214188 @default.
- W4319862245 hasConceptScore W4319862245C28490314 @default.
- W4319862245 hasConceptScore W4319862245C33923547 @default.
- W4319862245 hasConceptScore W4319862245C41008148 @default.
- W4319862245 hasConceptScore W4319862245C50644808 @default.
- W4319862245 hasConceptScore W4319862245C61445026 @default.
- W4319862245 hasConceptScore W4319862245C62520636 @default.
- W4319862245 hasLocation W43198622451 @default.
- W4319862245 hasLocation W43198622452 @default.
- W4319862245 hasOpenAccess W4319862245 @default.
- W4319862245 hasPrimaryLocation W43198622451 @default.
- W4319862245 hasRelatedWork W2028868645 @default.
- W4319862245 hasRelatedWork W2133817912 @default.
- W4319862245 hasRelatedWork W2386387936 @default.
- W4319862245 hasRelatedWork W2547993968 @default.
- W4319862245 hasRelatedWork W2765259565 @default.
- W4319862245 hasRelatedWork W2972767494 @default.
- W4319862245 hasRelatedWork W3093733783 @default.
- W4319862245 hasRelatedWork W3161296985 @default.
- W4319862245 hasRelatedWork W4206941387 @default.
- W4319862245 hasRelatedWork W4226321418 @default.
- W4319862245 isParatext "false" @default.