Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897915778> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2897915778 abstract "This paper proposes a Kullback-Leibler divergence (KLD) based recurrent mixture density network (RMDN) approach for acoustic modeling in emotional statistical parametric speech synthesis (SPSS), which aims at improving model accuracy and emotion naturalness. First, to improve model accuracy, we propose to use RMDN as acoustic model, which combines an LSTM with a mixture density network (MDN). Adding mixture density layer allows us to do multimodal regression as well as to predict variances, thus modeling more accurate probability density functions of acoustic features. Second, we further introduce Kullback-Leibler divergence regularization in model training. Inspired by KLD's success in acoustic model adaptation, we aim to improve the emotion naturalness by maximizing the distances between the distributions of emotional speech and neutral speech. Objective and subjective evaluations show that the proposed approach improves the prediction accuracy of acoustic features and the naturalness of the synthesized emotional speech." @default.
- W2897915778 created "2018-10-26" @default.
- W2897915778 creator A5009337933 @default.
- W2897915778 creator A5024778093 @default.
- W2897915778 creator A5033976028 @default.
- W2897915778 creator A5039991862 @default.
- W2897915778 creator A5042649425 @default.
- W2897915778 date "2018-10-19" @default.
- W2897915778 modified "2023-09-24" @default.
- W2897915778 title "A Kullback-Leibler Divergence Based Recurrent Mixture Density Network for Acoustic Modeling in Emotional Statistical Parametric Speech Synthesis" @default.
- W2897915778 cites W1499332833 @default.
- W2897915778 cites W1576227399 @default.
- W2897915778 cites W1965555277 @default.
- W2897915778 cites W1989549063 @default.
- W2897915778 cites W1990505856 @default.
- W2897915778 cites W1993267429 @default.
- W2897915778 cites W2046249308 @default.
- W2897915778 cites W2085013480 @default.
- W2897915778 cites W2129142580 @default.
- W2897915778 cites W2150658333 @default.
- W2897915778 cites W2255466643 @default.
- W2897915778 cites W2398071208 @default.
- W2897915778 cites W2402539796 @default.
- W2897915778 cites W2516321201 @default.
- W2897915778 cites W2680534654 @default.
- W2897915778 cites W2785364623 @default.
- W2897915778 cites W2787378487 @default.
- W2897915778 cites W2996765192 @default.
- W2897915778 cites W4252434905 @default.
- W2897915778 cites W2399853303 @default.
- W2897915778 doi "https://doi.org/10.1145/3267935.3267949" @default.
- W2897915778 hasPublicationYear "2018" @default.
- W2897915778 type Work @default.
- W2897915778 sameAs 2897915778 @default.
- W2897915778 citedByCount "0" @default.
- W2897915778 crossrefType "proceedings-article" @default.
- W2897915778 hasAuthorship W2897915778A5009337933 @default.
- W2897915778 hasAuthorship W2897915778A5024778093 @default.
- W2897915778 hasAuthorship W2897915778A5033976028 @default.
- W2897915778 hasAuthorship W2897915778A5039991862 @default.
- W2897915778 hasAuthorship W2897915778A5042649425 @default.
- W2897915778 hasConcept C105795698 @default.
- W2897915778 hasConcept C117251300 @default.
- W2897915778 hasConcept C138885662 @default.
- W2897915778 hasConcept C14999030 @default.
- W2897915778 hasConcept C154945302 @default.
- W2897915778 hasConcept C171752962 @default.
- W2897915778 hasConcept C207390915 @default.
- W2897915778 hasConcept C28490314 @default.
- W2897915778 hasConcept C33923547 @default.
- W2897915778 hasConcept C41008148 @default.
- W2897915778 hasConcept C41895202 @default.
- W2897915778 hasConceptScore W2897915778C105795698 @default.
- W2897915778 hasConceptScore W2897915778C117251300 @default.
- W2897915778 hasConceptScore W2897915778C138885662 @default.
- W2897915778 hasConceptScore W2897915778C14999030 @default.
- W2897915778 hasConceptScore W2897915778C154945302 @default.
- W2897915778 hasConceptScore W2897915778C171752962 @default.
- W2897915778 hasConceptScore W2897915778C207390915 @default.
- W2897915778 hasConceptScore W2897915778C28490314 @default.
- W2897915778 hasConceptScore W2897915778C33923547 @default.
- W2897915778 hasConceptScore W2897915778C41008148 @default.
- W2897915778 hasConceptScore W2897915778C41895202 @default.
- W2897915778 hasLocation W28979157781 @default.
- W2897915778 hasOpenAccess W2897915778 @default.
- W2897915778 hasPrimaryLocation W28979157781 @default.
- W2897915778 hasRelatedWork W1479948762 @default.
- W2897915778 hasRelatedWork W1995002252 @default.
- W2897915778 hasRelatedWork W2147126679 @default.
- W2897915778 hasRelatedWork W2156100129 @default.
- W2897915778 hasRelatedWork W2482033662 @default.
- W2897915778 hasRelatedWork W2794438528 @default.
- W2897915778 hasRelatedWork W2912843901 @default.
- W2897915778 hasRelatedWork W3149761360 @default.
- W2897915778 hasRelatedWork W3171304116 @default.
- W2897915778 hasRelatedWork W4287120475 @default.
- W2897915778 isParatext "false" @default.
- W2897915778 isRetracted "false" @default.
- W2897915778 magId "2897915778" @default.
- W2897915778 workType "article" @default.