Matches in SemOpenAlex for { <https://semopenalex.org/work/W2980577029> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W2980577029 abstract "Using neural networks to classify infant vocalisations into important subclasses (such as crying versus speech) is an emergent task in speech technology. One of the biggest roadblocks standing in the way of progress lies in the datasets: The performance of a learning model is affected by the labelling quality and size of the dataset used, and infant vocalisation datasets with good quality labels tend to be small. In this paper, we assess the performance of three models for infant VoCalisation Maturity (VCM) trained with a large dataset annotated automatically using a purpose-built classifier and a small dataset annotated by highly trained human coders. The two datasets are used in three different training strategies, whose performance is compared against a baseline model. The first training strategy investigates adversarial training, while the second exploits multi-task learning as the neural network trains on both datasets simultaneously. In the final strategy, we integrate adversarial training and multi-task learning. All of the training strategies outperform the baseline, with the adversarial training strategy yielding the best results on the development set." @default.
- W2980577029 created "2019-10-25" @default.
- W2980577029 creator A5019651318 @default.
- W2980577029 creator A5025997375 @default.
- W2980577029 creator A5036056631 @default.
- W2980577029 creator A5042831132 @default.
- W2980577029 creator A5080651988 @default.
- W2980577029 date "2019-10-14" @default.
- W2980577029 modified "2023-10-14" @default.
- W2980577029 title "VCMNet: Weakly Supervised Learning for Automatic Infant Vocalisation Maturity Analysis" @default.
- W2980577029 cites W2085662862 @default.
- W2980577029 cites W2109091525 @default.
- W2980577029 cites W2154163076 @default.
- W2980577029 cites W2162994165 @default.
- W2980577029 cites W2343593471 @default.
- W2980577029 cites W2512730320 @default.
- W2980577029 cites W2787658166 @default.
- W2980577029 cites W2937977583 @default.
- W2980577029 doi "https://doi.org/10.1145/3340555.3353751" @default.
- W2980577029 hasPublicationYear "2019" @default.
- W2980577029 type Work @default.
- W2980577029 sameAs 2980577029 @default.
- W2980577029 citedByCount "5" @default.
- W2980577029 countsByYear W29805770292021 @default.
- W2980577029 countsByYear W29805770292022 @default.
- W2980577029 countsByYear W29805770292023 @default.
- W2980577029 crossrefType "proceedings-article" @default.
- W2980577029 hasAuthorship W2980577029A5019651318 @default.
- W2980577029 hasAuthorship W2980577029A5025997375 @default.
- W2980577029 hasAuthorship W2980577029A5036056631 @default.
- W2980577029 hasAuthorship W2980577029A5042831132 @default.
- W2980577029 hasAuthorship W2980577029A5080651988 @default.
- W2980577029 hasBestOaLocation W29805770291 @default.
- W2980577029 hasConcept C101433766 @default.
- W2980577029 hasConcept C138496976 @default.
- W2980577029 hasConcept C154945302 @default.
- W2980577029 hasConcept C15744967 @default.
- W2980577029 hasConcept C41008148 @default.
- W2980577029 hasConceptScore W2980577029C101433766 @default.
- W2980577029 hasConceptScore W2980577029C138496976 @default.
- W2980577029 hasConceptScore W2980577029C154945302 @default.
- W2980577029 hasConceptScore W2980577029C15744967 @default.
- W2980577029 hasConceptScore W2980577029C41008148 @default.
- W2980577029 hasFunder F4320306076 @default.
- W2980577029 hasFunder F4320306183 @default.
- W2980577029 hasFunder F4320325505 @default.
- W2980577029 hasLocation W29805770291 @default.
- W2980577029 hasOpenAccess W2980577029 @default.
- W2980577029 hasPrimaryLocation W29805770291 @default.
- W2980577029 hasRelatedWork W2093578348 @default.
- W2980577029 hasRelatedWork W2096946506 @default.
- W2980577029 hasRelatedWork W2358668433 @default.
- W2980577029 hasRelatedWork W2376932109 @default.
- W2980577029 hasRelatedWork W2382290278 @default.
- W2980577029 hasRelatedWork W2390279801 @default.
- W2980577029 hasRelatedWork W2748952813 @default.
- W2980577029 hasRelatedWork W2766271392 @default.
- W2980577029 hasRelatedWork W2899084033 @default.
- W2980577029 hasRelatedWork W3107474891 @default.
- W2980577029 isParatext "false" @default.
- W2980577029 isRetracted "false" @default.
- W2980577029 magId "2980577029" @default.
- W2980577029 workType "article" @default.