Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285111045> ?p ?o ?g. }
- W4285111045 endingPage "1972" @default.
- W4285111045 startingPage "1959" @default.
- W4285111045 abstract "The prediction of valence from speech is an important, but challenging problem. The externalization of valence in speech has speaker-dependent cues, which contribute to performances that are often significantly lower than the prediction of other emotional attributes such as arousal and dominance. A practical approach to improve valence prediction from speech is to adapt the models to the target speakers in the test set. Adapting a speech emotion recognition (SER) system to a particular speaker is a hard problem, especially with deep neural networks (DNNs), since it requires optimizing millions of parameters. This study proposes an unsupervised approach to address this problem by searching for speakers in the train set with similar acoustic patterns as the speaker in the test set. Speech samples from the selected speakers are used to create the adaptation set. This approach leverages transfer learning using pre-trained models, which are adapted with these speech samples. We propose three alternative adaptation strategies: unique speaker, oversampling and weighting approaches. These methods differ on the use of the adaptation set in the personalization of the valence models. The results demonstrate that a valence prediction model can be efficiently personalized with these unsupervised approaches, leading to relative improvements as high as 13.52%." @default.
- W4285111045 created "2022-07-14" @default.
- W4285111045 creator A5006850523 @default.
- W4285111045 creator A5040793194 @default.
- W4285111045 date "2022-10-01" @default.
- W4285111045 modified "2023-10-14" @default.
- W4285111045 title "Unsupervised Personalization of an Emotion Recognition System: The Unique Properties of the Externalization of Valence in Speech" @default.
- W4285111045 cites W1517647818 @default.
- W4285111045 cites W1608705073 @default.
- W4285111045 cites W2010700035 @default.
- W4285111045 cites W2014399678 @default.
- W4285111045 cites W2028899742 @default.
- W4285111045 cites W2050752817 @default.
- W4285111045 cites W2071712938 @default.
- W4285111045 cites W2077953893 @default.
- W4285111045 cites W2089301222 @default.
- W4285111045 cites W2113087918 @default.
- W4285111045 cites W2129794709 @default.
- W4285111045 cites W2134031328 @default.
- W4285111045 cites W2144005487 @default.
- W4285111045 cites W2145589393 @default.
- W4285111045 cites W2146334809 @default.
- W4285111045 cites W2148146486 @default.
- W4285111045 cites W2156152318 @default.
- W4285111045 cites W2164186291 @default.
- W4285111045 cites W2284846286 @default.
- W4285111045 cites W2322208196 @default.
- W4285111045 cites W2342475039 @default.
- W4285111045 cites W2399733683 @default.
- W4285111045 cites W2401417847 @default.
- W4285111045 cites W2404205548 @default.
- W4285111045 cites W2404863510 @default.
- W4285111045 cites W2408021097 @default.
- W4285111045 cites W2525412388 @default.
- W4285111045 cites W2632855849 @default.
- W4285111045 cites W2742542661 @default.
- W4285111045 cites W2747172199 @default.
- W4285111045 cites W2767461737 @default.
- W4285111045 cites W2889100420 @default.
- W4285111045 cites W2890964092 @default.
- W4285111045 cites W2937833637 @default.
- W4285111045 cites W2952665519 @default.
- W4285111045 cites W2962839749 @default.
- W4285111045 cites W2963130397 @default.
- W4285111045 cites W2968228919 @default.
- W4285111045 cites W2973024936 @default.
- W4285111045 cites W2973126525 @default.
- W4285111045 cites W2979750667 @default.
- W4285111045 cites W2984270334 @default.
- W4285111045 doi "https://doi.org/10.1109/taffc.2022.3187336" @default.
- W4285111045 hasPublicationYear "2022" @default.
- W4285111045 type Work @default.
- W4285111045 citedByCount "3" @default.
- W4285111045 countsByYear W42851110452022 @default.
- W4285111045 countsByYear W42851110452023 @default.
- W4285111045 crossrefType "journal-article" @default.
- W4285111045 hasAuthorship W4285111045A5006850523 @default.
- W4285111045 hasAuthorship W4285111045A5040793194 @default.
- W4285111045 hasBestOaLocation W42851110451 @default.
- W4285111045 hasConcept C11171543 @default.
- W4285111045 hasConcept C121332964 @default.
- W4285111045 hasConcept C126838900 @default.
- W4285111045 hasConcept C136764020 @default.
- W4285111045 hasConcept C154945302 @default.
- W4285111045 hasConcept C15744967 @default.
- W4285111045 hasConcept C168900304 @default.
- W4285111045 hasConcept C169903167 @default.
- W4285111045 hasConcept C183003079 @default.
- W4285111045 hasConcept C183115368 @default.
- W4285111045 hasConcept C2779379281 @default.
- W4285111045 hasConcept C2781213101 @default.
- W4285111045 hasConcept C28490314 @default.
- W4285111045 hasConcept C41008148 @default.
- W4285111045 hasConcept C62520636 @default.
- W4285111045 hasConcept C71924100 @default.
- W4285111045 hasConceptScore W4285111045C11171543 @default.
- W4285111045 hasConceptScore W4285111045C121332964 @default.
- W4285111045 hasConceptScore W4285111045C126838900 @default.
- W4285111045 hasConceptScore W4285111045C136764020 @default.
- W4285111045 hasConceptScore W4285111045C154945302 @default.
- W4285111045 hasConceptScore W4285111045C15744967 @default.
- W4285111045 hasConceptScore W4285111045C168900304 @default.
- W4285111045 hasConceptScore W4285111045C169903167 @default.
- W4285111045 hasConceptScore W4285111045C183003079 @default.
- W4285111045 hasConceptScore W4285111045C183115368 @default.
- W4285111045 hasConceptScore W4285111045C2779379281 @default.
- W4285111045 hasConceptScore W4285111045C2781213101 @default.
- W4285111045 hasConceptScore W4285111045C28490314 @default.
- W4285111045 hasConceptScore W4285111045C41008148 @default.
- W4285111045 hasConceptScore W4285111045C62520636 @default.
- W4285111045 hasConceptScore W4285111045C71924100 @default.
- W4285111045 hasFunder F4320335353 @default.
- W4285111045 hasIssue "4" @default.
- W4285111045 hasLocation W42851110451 @default.
- W4285111045 hasLocation W42851110452 @default.
- W4285111045 hasLocation W42851110453 @default.
- W4285111045 hasOpenAccess W4285111045 @default.
- W4285111045 hasPrimaryLocation W42851110451 @default.