Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287777985> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4287777985 abstract "Motivated by the attention mechanism of the human visual system and recent developments in the field of machine translation, we introduce our attention-based and recurrent sequence to sequence autoencoders for fully unsupervised representation learning from audio files. In particular, we test the efficacy of our novel approach on the task of speech-based sleepiness recognition. We evaluate the learnt representations from both autoencoders, and then conduct an early fusion to ascertain possible complementarity between them. In our frameworks, we first extract Mel-spectrograms from raw audio files. Second, we train recurrent autoencoders on these spectrograms which are considered as time-dependent frequency vectors. Afterwards, we extract the activations of specific fully connected layers of the autoencoders which represent the learnt features of spectrograms for the corresponding audio instances. Finally, we train support vector regressors on these representations to obtain the predictions. On the development partition of the data, we achieve Spearman's correlation coefficients of .324, .283, and .320 with the targets on the Karolinska Sleepiness Scale by utilising attention and non-attention autoencoders, and the fusion of both autoencoders' representations, respectively. In the same order, we achieve .311, .359, and .367 Spearman's correlation coefficients on the test data, indicating the suitability of our proposed fusion strategy." @default.
- W4287777985 created "2022-07-26" @default.
- W4287777985 creator A5010754413 @default.
- W4287777985 creator A5017889477 @default.
- W4287777985 creator A5043060302 @default.
- W4287777985 creator A5061806139 @default.
- W4287777985 creator A5081697895 @default.
- W4287777985 creator A5091269736 @default.
- W4287777985 date "2020-05-15" @default.
- W4287777985 modified "2023-09-23" @default.
- W4287777985 title "A Novel Fusion of Attention and Sequence to Sequence Autoencoders to Predict Sleepiness From Speech" @default.
- W4287777985 doi "https://doi.org/10.48550/arxiv.2005.08722" @default.
- W4287777985 hasPublicationYear "2020" @default.
- W4287777985 type Work @default.
- W4287777985 citedByCount "0" @default.
- W4287777985 crossrefType "posted-content" @default.
- W4287777985 hasAuthorship W4287777985A5010754413 @default.
- W4287777985 hasAuthorship W4287777985A5017889477 @default.
- W4287777985 hasAuthorship W4287777985A5043060302 @default.
- W4287777985 hasAuthorship W4287777985A5061806139 @default.
- W4287777985 hasAuthorship W4287777985A5081697895 @default.
- W4287777985 hasAuthorship W4287777985A5091269736 @default.
- W4287777985 hasBestOaLocation W42877779851 @default.
- W4287777985 hasConcept C119857082 @default.
- W4287777985 hasConcept C153180895 @default.
- W4287777985 hasConcept C154945302 @default.
- W4287777985 hasConcept C202269582 @default.
- W4287777985 hasConcept C204321447 @default.
- W4287777985 hasConcept C2778112365 @default.
- W4287777985 hasConcept C28490314 @default.
- W4287777985 hasConcept C41008148 @default.
- W4287777985 hasConcept C45273575 @default.
- W4287777985 hasConcept C54355233 @default.
- W4287777985 hasConcept C86803240 @default.
- W4287777985 hasConceptScore W4287777985C119857082 @default.
- W4287777985 hasConceptScore W4287777985C153180895 @default.
- W4287777985 hasConceptScore W4287777985C154945302 @default.
- W4287777985 hasConceptScore W4287777985C202269582 @default.
- W4287777985 hasConceptScore W4287777985C204321447 @default.
- W4287777985 hasConceptScore W4287777985C2778112365 @default.
- W4287777985 hasConceptScore W4287777985C28490314 @default.
- W4287777985 hasConceptScore W4287777985C41008148 @default.
- W4287777985 hasConceptScore W4287777985C45273575 @default.
- W4287777985 hasConceptScore W4287777985C54355233 @default.
- W4287777985 hasConceptScore W4287777985C86803240 @default.
- W4287777985 hasLocation W42877779851 @default.
- W4287777985 hasOpenAccess W4287777985 @default.
- W4287777985 hasPrimaryLocation W42877779851 @default.
- W4287777985 hasRelatedWork W2138997758 @default.
- W4287777985 hasRelatedWork W2897924318 @default.
- W4287777985 hasRelatedWork W2961085424 @default.
- W4287777985 hasRelatedWork W2973062255 @default.
- W4287777985 hasRelatedWork W3107474891 @default.
- W4287777985 hasRelatedWork W3123210981 @default.
- W4287777985 hasRelatedWork W3156555204 @default.
- W4287777985 hasRelatedWork W4286629047 @default.
- W4287777985 hasRelatedWork W4306674287 @default.
- W4287777985 hasRelatedWork W4224009465 @default.
- W4287777985 isParatext "false" @default.
- W4287777985 isRetracted "false" @default.
- W4287777985 workType "article" @default.