Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286901870> ?p ?o ?g. }
Showing items 1 to 49 of
49
with 100 items per page.
- W4286901870 abstract "In this paper, we introduce DECAR (DEep Clustering for learning general-purpose Audio Representations), a self-supervised pre-training approach for learning general-purpose audio representations. Our system is based on clustering: it utilizes an offline clustering step to produce pseudo-labels and trains the network with a classification loss supervised by these pseudo-labels. We develop on top of recent advances in self-supervised learning for computer vision and design a lightweight, easy-to-use, self-supervised pre-training scheme for learning audio representations. We pre-train DECAR embeddings on a balanced subset of the large-scale AudioSet dataset and FSD50K and evaluate our representations on the LAPE Benchmark consisting of 11 downstream classification tasks, including speech, music, animal sounds, and acoustic scenes. Experimental results show that DECAR achieves results competitive to the state-of-the-art on both linear evaluation and transfer learning evaluation paradigms across all the downstream tasks in LAPE and performs better than other prior-art in literature with just 15% of the total amount of data available for pre-training. Furthermore, we conduct ablation studies identifying key design choices and also make all our code and pre-trained models publicly available" @default.
- W4286901870 created "2022-07-25" @default.
- W4286901870 creator A5027141199 @default.
- W4286901870 creator A5033408639 @default.
- W4286901870 creator A5048622819 @default.
- W4286901870 creator A5088973228 @default.
- W4286901870 date "2021-10-17" @default.
- W4286901870 modified "2023-09-26" @default.
- W4286901870 title "DECAR: Deep Clustering for learning general-purpose Audio Representations" @default.
- W4286901870 doi "https://doi.org/10.48550/arxiv.2110.08895" @default.
- W4286901870 hasPublicationYear "2021" @default.
- W4286901870 type Work @default.
- W4286901870 citedByCount "0" @default.
- W4286901870 crossrefType "posted-content" @default.
- W4286901870 hasAuthorship W4286901870A5027141199 @default.
- W4286901870 hasAuthorship W4286901870A5033408639 @default.
- W4286901870 hasAuthorship W4286901870A5048622819 @default.
- W4286901870 hasAuthorship W4286901870A5088973228 @default.
- W4286901870 hasBestOaLocation W42869018701 @default.
- W4286901870 hasConcept C119857082 @default.
- W4286901870 hasConcept C13280743 @default.
- W4286901870 hasConcept C154945302 @default.
- W4286901870 hasConcept C185798385 @default.
- W4286901870 hasConcept C205649164 @default.
- W4286901870 hasConcept C41008148 @default.
- W4286901870 hasConcept C73555534 @default.
- W4286901870 hasConceptScore W4286901870C119857082 @default.
- W4286901870 hasConceptScore W4286901870C13280743 @default.
- W4286901870 hasConceptScore W4286901870C154945302 @default.
- W4286901870 hasConceptScore W4286901870C185798385 @default.
- W4286901870 hasConceptScore W4286901870C205649164 @default.
- W4286901870 hasConceptScore W4286901870C41008148 @default.
- W4286901870 hasConceptScore W4286901870C73555534 @default.
- W4286901870 hasLocation W42869018701 @default.
- W4286901870 hasOpenAccess W4286901870 @default.
- W4286901870 hasPrimaryLocation W42869018701 @default.
- W4286901870 hasRelatedWork W112744582 @default.
- W4286901870 hasRelatedWork W1485630101 @default.
- W4286901870 hasRelatedWork W172869079 @default.
- W4286901870 hasRelatedWork W1834608617 @default.
- W4286901870 hasRelatedWork W2030059621 @default.
- W4286901870 hasRelatedWork W2498017833 @default.
- W4286901870 hasRelatedWork W2961085424 @default.
- W4286901870 hasRelatedWork W4200446208 @default.
- W4286901870 hasRelatedWork W4286629047 @default.
- W4286901870 hasRelatedWork W4224009465 @default.
- W4286901870 isParatext "false" @default.
- W4286901870 isRetracted "false" @default.
- W4286901870 workType "article" @default.