Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950161879> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2950161879 abstract "This paper presents a method of using autoregressive neural networks for the acoustic modeling of singing voice synthesis (SVS). Singing voice differs from speech and it contains more local dynamic movements of acoustic features, e.g., vibratos. Therefore, our method adopts deep autoregressive (DAR) models to predict the F0 and spectral features of singing voice in order to better describe the dependencies among the acoustic features of consecutive frames. For F0 modeling, discretized F0 values are used and the influences of the history length in DAR are analyzed by experiments. An F0 post-processing strategy is also designed to alleviate the inconsistency between the predicted F0 contours and the F0 values determined by music notes. Furthermore, we extend the DAR model to deal with continuous spectral features, and a prenet module with self-attention layers is introduced to process historical frames. Experiments on a Chinese singing voice corpus demonstrate that our method using DARs can produce F0 contours with vibratos effectively, and can achieve better objective and subjective performance than the conventional method using recurrent neural networks (RNNs)." @default.
- W2950161879 created "2019-06-27" @default.
- W2950161879 creator A5045907056 @default.
- W2950161879 creator A5057227915 @default.
- W2950161879 creator A5059767940 @default.
- W2950161879 creator A5087844105 @default.
- W2950161879 date "2019-06-21" @default.
- W2950161879 modified "2023-10-16" @default.
- W2950161879 title "Singing Voice Synthesis Using Deep Autoregressive Neural Networks for Acoustic Modeling" @default.
- W2950161879 cites W1522301498 @default.
- W2950161879 cites W1576227399 @default.
- W2950161879 cites W1990505856 @default.
- W2950161879 cites W2007463795 @default.
- W2950161879 cites W2049686551 @default.
- W2950161879 cites W2072389495 @default.
- W2950161879 cites W2095705004 @default.
- W2950161879 cites W2112656927 @default.
- W2950161879 cites W2515336442 @default.
- W2950161879 cites W2516406502 @default.
- W2950161879 cites W2604184139 @default.
- W2950161879 cites W2606052883 @default.
- W2950161879 cites W2608207374 @default.
- W2950161879 cites W2788851830 @default.
- W2950161879 cites W2801493797 @default.
- W2950161879 cites W2889244839 @default.
- W2950161879 cites W2949117887 @default.
- W2950161879 cites W2949382160 @default.
- W2950161879 cites W2963403868 @default.
- W2950161879 cites W36903255 @default.
- W2950161879 cites W1871497677 @default.
- W2950161879 doi "https://doi.org/10.48550/arxiv.1906.08977" @default.
- W2950161879 hasPublicationYear "2019" @default.
- W2950161879 type Work @default.
- W2950161879 sameAs 2950161879 @default.
- W2950161879 citedByCount "7" @default.
- W2950161879 countsByYear W29501618792019 @default.
- W2950161879 countsByYear W29501618792020 @default.
- W2950161879 crossrefType "posted-content" @default.
- W2950161879 hasAuthorship W2950161879A5045907056 @default.
- W2950161879 hasAuthorship W2950161879A5057227915 @default.
- W2950161879 hasAuthorship W2950161879A5059767940 @default.
- W2950161879 hasAuthorship W2950161879A5087844105 @default.
- W2950161879 hasBestOaLocation W29501618791 @default.
- W2950161879 hasConcept C111919701 @default.
- W2950161879 hasConcept C121332964 @default.
- W2950161879 hasConcept C147168706 @default.
- W2950161879 hasConcept C149782125 @default.
- W2950161879 hasConcept C14999030 @default.
- W2950161879 hasConcept C154945302 @default.
- W2950161879 hasConcept C159877910 @default.
- W2950161879 hasConcept C24890656 @default.
- W2950161879 hasConcept C28490314 @default.
- W2950161879 hasConcept C33923547 @default.
- W2950161879 hasConcept C41008148 @default.
- W2950161879 hasConcept C44819458 @default.
- W2950161879 hasConcept C50644808 @default.
- W2950161879 hasConcept C98045186 @default.
- W2950161879 hasConceptScore W2950161879C111919701 @default.
- W2950161879 hasConceptScore W2950161879C121332964 @default.
- W2950161879 hasConceptScore W2950161879C147168706 @default.
- W2950161879 hasConceptScore W2950161879C149782125 @default.
- W2950161879 hasConceptScore W2950161879C14999030 @default.
- W2950161879 hasConceptScore W2950161879C154945302 @default.
- W2950161879 hasConceptScore W2950161879C159877910 @default.
- W2950161879 hasConceptScore W2950161879C24890656 @default.
- W2950161879 hasConceptScore W2950161879C28490314 @default.
- W2950161879 hasConceptScore W2950161879C33923547 @default.
- W2950161879 hasConceptScore W2950161879C41008148 @default.
- W2950161879 hasConceptScore W2950161879C44819458 @default.
- W2950161879 hasConceptScore W2950161879C50644808 @default.
- W2950161879 hasConceptScore W2950161879C98045186 @default.
- W2950161879 hasLocation W29501618791 @default.
- W2950161879 hasOpenAccess W2950161879 @default.
- W2950161879 hasPrimaryLocation W29501618791 @default.
- W2950161879 hasRelatedWork W1705321970 @default.
- W2950161879 hasRelatedWork W2108382268 @default.
- W2950161879 hasRelatedWork W2146639687 @default.
- W2950161879 hasRelatedWork W2153405461 @default.
- W2950161879 hasRelatedWork W2547993968 @default.
- W2950161879 hasRelatedWork W2549780086 @default.
- W2950161879 hasRelatedWork W2921857201 @default.
- W2950161879 hasRelatedWork W2945705471 @default.
- W2950161879 hasRelatedWork W2950161879 @default.
- W2950161879 hasRelatedWork W2951961943 @default.
- W2950161879 isParatext "false" @default.
- W2950161879 isRetracted "false" @default.
- W2950161879 magId "2950161879" @default.
- W2950161879 workType "article" @default.