Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963175743> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2963175743 abstract "Neural waveform models such as the WaveNet are used in many recent text-to-speech systems, but the original WaveNet is quite slow in waveform generation because of its autoregressive (AR) structure. Although faster non-AR models were recently reported, they may be prohibitively complicated due to the use of a distilling training method and the blend of other disparate training criteria. This study proposes a non-AR neural source-filter waveform model that can be directly trained using spectrum-based training criteria and the stochastic gradient descent method. Given the input acoustic features, the proposed model first uses a source module to generate a sine-based excitation signal and then uses a filter module to transform the excitation signal into the output speech waveform. Our experiments demonstrated that the proposed model generated waveforms at least 100 times faster than the AR WaveNet and the quality of its synthetic speech is close to that of speech generated by the AR WaveNet. Ablation test results showed that both the sine-wave excitation signal and the spectrum-based training criteria were essential to the performance of the proposed model." @default.
- W2963175743 created "2019-07-30" @default.
- W2963175743 creator A5006822602 @default.
- W2963175743 creator A5007639385 @default.
- W2963175743 creator A5062895056 @default.
- W2963175743 date "2019-05-01" @default.
- W2963175743 modified "2023-09-24" @default.
- W2963175743 title "Neural Source-filter-based Waveform Model for Statistical Parametric Speech Synthesis" @default.
- W2963175743 cites W1496971974 @default.
- W2963175743 cites W1594680456 @default.
- W2963175743 cites W1976313025 @default.
- W2963175743 cites W2003513484 @default.
- W2963175743 cites W2164764235 @default.
- W2963175743 cites W2194775991 @default.
- W2963175743 cites W2405614646 @default.
- W2963175743 cites W2471520273 @default.
- W2963175743 cites W2749651610 @default.
- W2963175743 cites W2749881488 @default.
- W2963175743 cites W2886022419 @default.
- W2963175743 cites W2963522141 @default.
- W2963175743 cites W2964041258 @default.
- W2963175743 cites W2964243274 @default.
- W2963175743 doi "https://doi.org/10.1109/icassp.2019.8682298" @default.
- W2963175743 hasPublicationYear "2019" @default.
- W2963175743 type Work @default.
- W2963175743 sameAs 2963175743 @default.
- W2963175743 citedByCount "89" @default.
- W2963175743 countsByYear W29631757432018 @default.
- W2963175743 countsByYear W29631757432019 @default.
- W2963175743 countsByYear W29631757432020 @default.
- W2963175743 countsByYear W29631757432021 @default.
- W2963175743 countsByYear W29631757432022 @default.
- W2963175743 countsByYear W29631757432023 @default.
- W2963175743 crossrefType "proceedings-article" @default.
- W2963175743 hasAuthorship W2963175743A5006822602 @default.
- W2963175743 hasAuthorship W2963175743A5007639385 @default.
- W2963175743 hasAuthorship W2963175743A5062895056 @default.
- W2963175743 hasBestOaLocation W29631757432 @default.
- W2963175743 hasConcept C105795698 @default.
- W2963175743 hasConcept C106131492 @default.
- W2963175743 hasConcept C117251300 @default.
- W2963175743 hasConcept C149782125 @default.
- W2963175743 hasConcept C14999030 @default.
- W2963175743 hasConcept C154945302 @default.
- W2963175743 hasConcept C159877910 @default.
- W2963175743 hasConcept C197424946 @default.
- W2963175743 hasConcept C199360897 @default.
- W2963175743 hasConcept C206688291 @default.
- W2963175743 hasConcept C2779843651 @default.
- W2963175743 hasConcept C28490314 @default.
- W2963175743 hasConcept C31972630 @default.
- W2963175743 hasConcept C33923547 @default.
- W2963175743 hasConcept C41008148 @default.
- W2963175743 hasConcept C50644808 @default.
- W2963175743 hasConcept C554190296 @default.
- W2963175743 hasConcept C76155785 @default.
- W2963175743 hasConceptScore W2963175743C105795698 @default.
- W2963175743 hasConceptScore W2963175743C106131492 @default.
- W2963175743 hasConceptScore W2963175743C117251300 @default.
- W2963175743 hasConceptScore W2963175743C149782125 @default.
- W2963175743 hasConceptScore W2963175743C14999030 @default.
- W2963175743 hasConceptScore W2963175743C154945302 @default.
- W2963175743 hasConceptScore W2963175743C159877910 @default.
- W2963175743 hasConceptScore W2963175743C197424946 @default.
- W2963175743 hasConceptScore W2963175743C199360897 @default.
- W2963175743 hasConceptScore W2963175743C206688291 @default.
- W2963175743 hasConceptScore W2963175743C2779843651 @default.
- W2963175743 hasConceptScore W2963175743C28490314 @default.
- W2963175743 hasConceptScore W2963175743C31972630 @default.
- W2963175743 hasConceptScore W2963175743C33923547 @default.
- W2963175743 hasConceptScore W2963175743C41008148 @default.
- W2963175743 hasConceptScore W2963175743C50644808 @default.
- W2963175743 hasConceptScore W2963175743C554190296 @default.
- W2963175743 hasConceptScore W2963175743C76155785 @default.
- W2963175743 hasLocation W29631757431 @default.
- W2963175743 hasLocation W29631757432 @default.
- W2963175743 hasOpenAccess W2963175743 @default.
- W2963175743 hasPrimaryLocation W29631757431 @default.
- W2963175743 hasRelatedWork W2069049662 @default.
- W2963175743 hasRelatedWork W2473236733 @default.
- W2963175743 hasRelatedWork W2610284765 @default.
- W2963175743 hasRelatedWork W2803229097 @default.
- W2963175743 hasRelatedWork W2912843901 @default.
- W2963175743 hasRelatedWork W2929299742 @default.
- W2963175743 hasRelatedWork W2963015453 @default.
- W2963175743 hasRelatedWork W3171304116 @default.
- W2963175743 hasRelatedWork W4223645605 @default.
- W2963175743 hasRelatedWork W4287120475 @default.
- W2963175743 isParatext "false" @default.
- W2963175743 isRetracted "false" @default.
- W2963175743 magId "2963175743" @default.
- W2963175743 workType "article" @default.