Matches in SemOpenAlex for { <https://semopenalex.org/work/W2802076562> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2802076562 abstract "Head movement is an integral part of face-to-face communications. It is important to investigate methodologies to generate naturalistic movements for conversational agents (CAs). The predominant method for head movement generation is using rules based on the meaning of the message. However, the variations of head movements by these methods are bounded by the predefined dictionary of gestures. Speech-driven methods offer an alternative approach, learning the relationship between speech and head movements from real recordings. However, previous studies do not generate novel realizations for a repeated speech signal. Conditional generative adversarial network (GAN) provides a framework to generate multiple realizations of head movements for each speech segment by sampling from a conditioned distribution. We build a conditional GAN with bidirectional long-short term memory (BLSTM), which is suitable for capturing the long-short term dependencies of time-continuous signals. This model learns the distribution of head movements conditioned on speech prosodic features. We compare this model with a dynamic Bayesian network (DBN) and BLSTM models optimized to reduce mean squared error (MSE) or to increase concordance correlation. The objective evaluations and subjective evaluations of the results showed better performance for the conditional GAN model compared with these baseline systems." @default.
- W2802076562 created "2018-05-17" @default.
- W2802076562 creator A5001956187 @default.
- W2802076562 creator A5040793194 @default.
- W2802076562 date "2018-04-01" @default.
- W2802076562 modified "2023-09-26" @default.
- W2802076562 title "Novel Realizations of Speech-Driven Head Movements with Generative Adversarial Networks" @default.
- W2802076562 cites W1918373437 @default.
- W2802076562 cites W1974597084 @default.
- W2802076562 cites W1975798038 @default.
- W2802076562 cites W1999681822 @default.
- W2802076562 cites W2024536104 @default.
- W2802076562 cites W2027454453 @default.
- W2802076562 cites W2064675550 @default.
- W2802076562 cites W2083731490 @default.
- W2802076562 cites W2117752179 @default.
- W2802076562 cites W2118004237 @default.
- W2802076562 cites W2124399597 @default.
- W2802076562 cites W2127365090 @default.
- W2802076562 cites W2146334809 @default.
- W2802076562 cites W2296371640 @default.
- W2802076562 cites W2404535984 @default.
- W2802076562 cites W2741633070 @default.
- W2802076562 cites W2745980686 @default.
- W2802076562 doi "https://doi.org/10.1109/icassp.2018.8461967" @default.
- W2802076562 hasPublicationYear "2018" @default.
- W2802076562 type Work @default.
- W2802076562 sameAs 2802076562 @default.
- W2802076562 citedByCount "41" @default.
- W2802076562 countsByYear W28020765622018 @default.
- W2802076562 countsByYear W28020765622019 @default.
- W2802076562 countsByYear W28020765622020 @default.
- W2802076562 countsByYear W28020765622021 @default.
- W2802076562 countsByYear W28020765622022 @default.
- W2802076562 countsByYear W28020765622023 @default.
- W2802076562 crossrefType "proceedings-article" @default.
- W2802076562 hasAuthorship W2802076562A5001956187 @default.
- W2802076562 hasAuthorship W2802076562A5040793194 @default.
- W2802076562 hasConcept C107673813 @default.
- W2802076562 hasConcept C114793014 @default.
- W2802076562 hasConcept C119857082 @default.
- W2802076562 hasConcept C127313418 @default.
- W2802076562 hasConcept C144024400 @default.
- W2802076562 hasConcept C153180895 @default.
- W2802076562 hasConcept C154945302 @default.
- W2802076562 hasConcept C207347870 @default.
- W2802076562 hasConcept C23224414 @default.
- W2802076562 hasConcept C2779304628 @default.
- W2802076562 hasConcept C2780312720 @default.
- W2802076562 hasConcept C28490314 @default.
- W2802076562 hasConcept C36289849 @default.
- W2802076562 hasConcept C41008148 @default.
- W2802076562 hasConcept C82142266 @default.
- W2802076562 hasConceptScore W2802076562C107673813 @default.
- W2802076562 hasConceptScore W2802076562C114793014 @default.
- W2802076562 hasConceptScore W2802076562C119857082 @default.
- W2802076562 hasConceptScore W2802076562C127313418 @default.
- W2802076562 hasConceptScore W2802076562C144024400 @default.
- W2802076562 hasConceptScore W2802076562C153180895 @default.
- W2802076562 hasConceptScore W2802076562C154945302 @default.
- W2802076562 hasConceptScore W2802076562C207347870 @default.
- W2802076562 hasConceptScore W2802076562C23224414 @default.
- W2802076562 hasConceptScore W2802076562C2779304628 @default.
- W2802076562 hasConceptScore W2802076562C2780312720 @default.
- W2802076562 hasConceptScore W2802076562C28490314 @default.
- W2802076562 hasConceptScore W2802076562C36289849 @default.
- W2802076562 hasConceptScore W2802076562C41008148 @default.
- W2802076562 hasConceptScore W2802076562C82142266 @default.
- W2802076562 hasLocation W28020765621 @default.
- W2802076562 hasOpenAccess W2802076562 @default.
- W2802076562 hasPrimaryLocation W28020765621 @default.
- W2802076562 hasRelatedWork W2963001579 @default.
- W2802076562 hasRelatedWork W2998996837 @default.
- W2802076562 hasRelatedWork W3017161950 @default.
- W2802076562 hasRelatedWork W3022379890 @default.
- W2802076562 hasRelatedWork W3034163353 @default.
- W2802076562 hasRelatedWork W3039718605 @default.
- W2802076562 hasRelatedWork W3107474891 @default.
- W2802076562 hasRelatedWork W3156291593 @default.
- W2802076562 hasRelatedWork W3181034584 @default.
- W2802076562 hasRelatedWork W4220812973 @default.
- W2802076562 isParatext "false" @default.
- W2802076562 isRetracted "false" @default.
- W2802076562 magId "2802076562" @default.
- W2802076562 workType "article" @default.