Matches in SemOpenAlex for { <https://semopenalex.org/work/W2804119478> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2804119478 abstract "Age estimation from speech recently received a lot of attention. Approaches such as i-vectors and deep learning have been successfully applied to this task achieving great performance. However, one drawback of those methods is that they produce a hard age estimation without any kind of confidence measure about the quality of the prediction. Designing systems with the ability to provide a confidence measure about their output is extremely valuable for several applications where the cost of making bad decisions is worse than making no decision, e.g., forensics. In this paper, we propose a novel framework to jointly predict the age and its estimation uncertainty in a context of neural regression model. This model is trained using probabilistic fashion instead of using the classical minimum mean square error objective used for regression tasks. The probabilistic output corresponds to a Gaussian posterior. The proposed neural network will estimate both the posterior mean which corresponds to the predicted age and the variance which quantifies the uncertainty of the prediction. We evaluated our approach on two different datasets NIST SRE 2008 − 2010 and Switchboard." @default.
- W2804119478 created "2018-06-01" @default.
- W2804119478 creator A5050632169 @default.
- W2804119478 creator A5057010207 @default.
- W2804119478 creator A5060644900 @default.
- W2804119478 creator A5071702566 @default.
- W2804119478 date "2018-04-01" @default.
- W2804119478 modified "2023-09-27" @default.
- W2804119478 title "Measuring Uncertainty in Deep Regression Models: The Case of Age Estimation from Speech" @default.
- W2804119478 doi "https://doi.org/10.1109/icassp.2018.8462416" @default.
- W2804119478 hasPublicationYear "2018" @default.
- W2804119478 type Work @default.
- W2804119478 sameAs 2804119478 @default.
- W2804119478 citedByCount "0" @default.
- W2804119478 crossrefType "proceedings-article" @default.
- W2804119478 hasAuthorship W2804119478A5050632169 @default.
- W2804119478 hasAuthorship W2804119478A5057010207 @default.
- W2804119478 hasAuthorship W2804119478A5060644900 @default.
- W2804119478 hasAuthorship W2804119478A5071702566 @default.
- W2804119478 hasConcept C105795698 @default.
- W2804119478 hasConcept C111219384 @default.
- W2804119478 hasConcept C119857082 @default.
- W2804119478 hasConcept C121955636 @default.
- W2804119478 hasConcept C124101348 @default.
- W2804119478 hasConcept C139945424 @default.
- W2804119478 hasConcept C144133560 @default.
- W2804119478 hasConcept C151730666 @default.
- W2804119478 hasConcept C152877465 @default.
- W2804119478 hasConcept C154945302 @default.
- W2804119478 hasConcept C162324750 @default.
- W2804119478 hasConcept C187736073 @default.
- W2804119478 hasConcept C196083921 @default.
- W2804119478 hasConcept C2779343474 @default.
- W2804119478 hasConcept C2780009758 @default.
- W2804119478 hasConcept C2780451532 @default.
- W2804119478 hasConcept C28490314 @default.
- W2804119478 hasConcept C33923547 @default.
- W2804119478 hasConcept C41008148 @default.
- W2804119478 hasConcept C49937458 @default.
- W2804119478 hasConcept C50644808 @default.
- W2804119478 hasConcept C83546350 @default.
- W2804119478 hasConcept C86803240 @default.
- W2804119478 hasConceptScore W2804119478C105795698 @default.
- W2804119478 hasConceptScore W2804119478C111219384 @default.
- W2804119478 hasConceptScore W2804119478C119857082 @default.
- W2804119478 hasConceptScore W2804119478C121955636 @default.
- W2804119478 hasConceptScore W2804119478C124101348 @default.
- W2804119478 hasConceptScore W2804119478C139945424 @default.
- W2804119478 hasConceptScore W2804119478C144133560 @default.
- W2804119478 hasConceptScore W2804119478C151730666 @default.
- W2804119478 hasConceptScore W2804119478C152877465 @default.
- W2804119478 hasConceptScore W2804119478C154945302 @default.
- W2804119478 hasConceptScore W2804119478C162324750 @default.
- W2804119478 hasConceptScore W2804119478C187736073 @default.
- W2804119478 hasConceptScore W2804119478C196083921 @default.
- W2804119478 hasConceptScore W2804119478C2779343474 @default.
- W2804119478 hasConceptScore W2804119478C2780009758 @default.
- W2804119478 hasConceptScore W2804119478C2780451532 @default.
- W2804119478 hasConceptScore W2804119478C28490314 @default.
- W2804119478 hasConceptScore W2804119478C33923547 @default.
- W2804119478 hasConceptScore W2804119478C41008148 @default.
- W2804119478 hasConceptScore W2804119478C49937458 @default.
- W2804119478 hasConceptScore W2804119478C50644808 @default.
- W2804119478 hasConceptScore W2804119478C83546350 @default.
- W2804119478 hasConceptScore W2804119478C86803240 @default.
- W2804119478 hasLocation W28041194781 @default.
- W2804119478 hasOpenAccess W2804119478 @default.
- W2804119478 hasPrimaryLocation W28041194781 @default.
- W2804119478 hasRelatedWork W1556469941 @default.
- W2804119478 hasRelatedWork W2066558815 @default.
- W2804119478 hasRelatedWork W2158890694 @default.
- W2804119478 hasRelatedWork W2353645903 @default.
- W2804119478 hasRelatedWork W2479959943 @default.
- W2804119478 hasRelatedWork W2524200052 @default.
- W2804119478 hasRelatedWork W255309579 @default.
- W2804119478 hasRelatedWork W2743629318 @default.
- W2804119478 hasRelatedWork W2809348641 @default.
- W2804119478 hasRelatedWork W2938753501 @default.
- W2804119478 hasRelatedWork W3015993000 @default.
- W2804119478 hasRelatedWork W3038849371 @default.
- W2804119478 hasRelatedWork W3080262470 @default.
- W2804119478 hasRelatedWork W310121661 @default.
- W2804119478 hasRelatedWork W3104651881 @default.
- W2804119478 hasRelatedWork W3120390462 @default.
- W2804119478 hasRelatedWork W3127857540 @default.
- W2804119478 hasRelatedWork W3149210817 @default.
- W2804119478 hasRelatedWork W3152782420 @default.
- W2804119478 hasRelatedWork W3182751885 @default.
- W2804119478 isParatext "false" @default.
- W2804119478 isRetracted "false" @default.
- W2804119478 magId "2804119478" @default.
- W2804119478 workType "article" @default.