Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385491567> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4385491567 abstract "Existing research on audio–text retrieval is limited by the size of the dataset and the structure of the network, making it difficult to learn the ideal features of audio and text resulting in low retrieval accuracy. In this paper, we construct an audio–text retrieval model based on contrastive learning and collaborative attention mechanism. We first reduce model overfitting by implementing audio augmentation strategies including adding Gaussian noise, adjusting the pitch and changing the time shift. Additionally, we design a co-attentive mechanism module that the audio data and text data guide each other in feature learning, effectively capturing the connection between the audio modality and the text modality. Finally, we apply the contrastive learning methods between the augmented audio data and the original audio, allowing the model to effectively learn a richer set of audio features. The retrieval accuracy of our proposed model is significantly improved on publicly available datasets AudioCaps and Clotho." @default.
- W4385491567 created "2023-08-03" @default.
- W4385491567 creator A5023107764 @default.
- W4385491567 creator A5024949205 @default.
- W4385491567 creator A5059560888 @default.
- W4385491567 creator A5060614711 @default.
- W4385491567 date "2023-08-02" @default.
- W4385491567 modified "2023-09-27" @default.
- W4385491567 title "Audio–text retrieval based on contrastive learning and collaborative attention mechanism" @default.
- W4385491567 cites W1963897898 @default.
- W4385491567 cites W2104887782 @default.
- W4385491567 cites W2137400100 @default.
- W4385491567 cites W2142352693 @default.
- W4385491567 cites W2161947961 @default.
- W4385491567 cites W2165548826 @default.
- W4385491567 cites W2266728343 @default.
- W4385491567 cites W2798991696 @default.
- W4385491567 cites W2963187862 @default.
- W4385491567 cites W2963435138 @default.
- W4385491567 cites W2972513594 @default.
- W4385491567 cites W2979579363 @default.
- W4385491567 cites W2987172297 @default.
- W4385491567 cites W3004146833 @default.
- W4385491567 cites W3015591594 @default.
- W4385491567 cites W3015791137 @default.
- W4385491567 cites W3026732421 @default.
- W4385491567 cites W3105204788 @default.
- W4385491567 cites W3108655343 @default.
- W4385491567 cites W3125113672 @default.
- W4385491567 cites W3137758952 @default.
- W4385491567 cites W3157352387 @default.
- W4385491567 cites W3162583214 @default.
- W4385491567 cites W3174525637 @default.
- W4385491567 cites W3198452188 @default.
- W4385491567 cites W4221157007 @default.
- W4385491567 cites W4224933373 @default.
- W4385491567 cites W4312463400 @default.
- W4385491567 cites W4312999114 @default.
- W4385491567 doi "https://doi.org/10.1007/s00530-023-01144-4" @default.
- W4385491567 hasPublicationYear "2023" @default.
- W4385491567 type Work @default.
- W4385491567 citedByCount "0" @default.
- W4385491567 crossrefType "journal-article" @default.
- W4385491567 hasAuthorship W4385491567A5023107764 @default.
- W4385491567 hasAuthorship W4385491567A5024949205 @default.
- W4385491567 hasAuthorship W4385491567A5059560888 @default.
- W4385491567 hasAuthorship W4385491567A5060614711 @default.
- W4385491567 hasBestOaLocation W43854915672 @default.
- W4385491567 hasConcept C154945302 @default.
- W4385491567 hasConcept C177264268 @default.
- W4385491567 hasConcept C199360897 @default.
- W4385491567 hasConcept C22019652 @default.
- W4385491567 hasConcept C2780226545 @default.
- W4385491567 hasConcept C28490314 @default.
- W4385491567 hasConcept C41008148 @default.
- W4385491567 hasConcept C50644808 @default.
- W4385491567 hasConceptScore W4385491567C154945302 @default.
- W4385491567 hasConceptScore W4385491567C177264268 @default.
- W4385491567 hasConceptScore W4385491567C199360897 @default.
- W4385491567 hasConceptScore W4385491567C22019652 @default.
- W4385491567 hasConceptScore W4385491567C2780226545 @default.
- W4385491567 hasConceptScore W4385491567C28490314 @default.
- W4385491567 hasConceptScore W4385491567C41008148 @default.
- W4385491567 hasConceptScore W4385491567C50644808 @default.
- W4385491567 hasFunder F4320328713 @default.
- W4385491567 hasLocation W43854915671 @default.
- W4385491567 hasLocation W43854915672 @default.
- W4385491567 hasOpenAccess W4385491567 @default.
- W4385491567 hasPrimaryLocation W43854915671 @default.
- W4385491567 hasRelatedWork W2767651786 @default.
- W4385491567 hasRelatedWork W2792213864 @default.
- W4385491567 hasRelatedWork W2885665929 @default.
- W4385491567 hasRelatedWork W2989932438 @default.
- W4385491567 hasRelatedWork W3035162004 @default.
- W4385491567 hasRelatedWork W3081496756 @default.
- W4385491567 hasRelatedWork W3099765033 @default.
- W4385491567 hasRelatedWork W3102792585 @default.
- W4385491567 hasRelatedWork W4224929651 @default.
- W4385491567 hasRelatedWork W4285802257 @default.
- W4385491567 isParatext "false" @default.
- W4385491567 isRetracted "false" @default.
- W4385491567 workType "article" @default.