FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890913619> ?p ?o ?g. }

• W2890913619 endingPage "441" @default.
• W2890913619 startingPage "429" @default.
• W2890913619 abstract "Conventional methods for finding audio in databases typically search text labels, rather than the audio itself. This can be problematic as labels may be missing, irrelevant to the audio content, or not known by users. Query by vocal imitation lets users query using vocal imitations instead. To do so, appropriate audio feature representations and effective similarity measures of imitations and original sounds must be developed. In this paper, we build upon our preliminary work to propose Siamese style convolutional neural networks to learn feature representations and similarity measures in a unified end-to-end training framework. Our Siamese architecture uses two convolutional neural networks to extract features, one from vocal imitations and the other from original sounds. The encoded features are then concatenated and fed into a fully connected network to estimate their similarity. We propose two versions of the system: IMINET is symmetric where the two encoders have an identical structure and are trained from scratch, while TL-IMINET is asymmetric and adopts the transfer learning idea by pretraining the two encoders from other relevant tasks: spoken language recognition for the imitation encoder and environmental sound classification for the original sound encoder. Experimental results show that both versions of the proposed system outperform a state-of-the-art system for sound search by vocal imitation, and the performance can be further improved when they are fused with the state of the art system. Results also show that transfer learning significantly improves the retrieval performance. This paper also provides insights to the proposed networks by visualizing and sonifying input patterns that maximize the activation of certain neurons in different layers." @default.
• W2890913619 created "2018-09-27" @default.
• W2890913619 creator A5006409712 @default.
• W2890913619 creator A5027406828 @default.
• W2890913619 creator A5078699661 @default.
• W2890913619 date "2019-02-01" @default.
• W2890913619 modified "2023-10-14" @default.
• W2890913619 title "Siamese Style Convolutional Neural Networks for Sound Search by Vocal Imitation" @default.
• W2890913619 cites W1965555277 @default.
• W2890913619 cites W1977863522 @default.
• W2890913619 cites W1988566301 @default.
• W2890913619 cites W2000420612 @default.
• W2890913619 cites W2008066450 @default.
• W2890913619 cites W2025763800 @default.
• W2890913619 cites W2027518030 @default.
• W2890913619 cites W2054139811 @default.
• W2890913619 cites W2100495367 @default.
• W2890913619 cites W2100805904 @default.
• W2890913619 cites W2102605133 @default.
• W2890913619 cites W2103219113 @default.
• W2890913619 cites W2120847449 @default.
• W2890913619 cites W2128160875 @default.
• W2890913619 cites W2130325614 @default.
• W2890913619 cites W2138286601 @default.
• W2890913619 cites W2146229144 @default.
• W2890913619 cites W2157364932 @default.
• W2890913619 cites W2167700723 @default.
• W2890913619 cites W2406791552 @default.
• W2890913619 cites W2517544051 @default.
• W2890913619 cites W2618530766 @default.
• W2890913619 cites W2625466441 @default.
• W2890913619 cites W2775430159 @default.
• W2890913619 cites W2889726676 @default.
• W2890913619 cites W3098357269 @default.
• W2890913619 cites W4253453573 @default.
• W2890913619 doi "https://doi.org/10.1109/taslp.2018.2868428" @default.
• W2890913619 hasPublicationYear "2019" @default.
• W2890913619 type Work @default.
• W2890913619 sameAs 2890913619 @default.
• W2890913619 citedByCount "21" @default.
• W2890913619 countsByYear W28909136192018 @default.
• W2890913619 countsByYear W28909136192019 @default.
• W2890913619 countsByYear W28909136192020 @default.
• W2890913619 countsByYear W28909136192021 @default.
• W2890913619 countsByYear W28909136192022 @default.
• W2890913619 countsByYear W28909136192023 @default.
• W2890913619 crossrefType "journal-article" @default.
• W2890913619 hasAuthorship W2890913619A5006409712 @default.
• W2890913619 hasAuthorship W2890913619A5027406828 @default.
• W2890913619 hasAuthorship W2890913619A5078699661 @default.
• W2890913619 hasBestOaLocation W28909136191 @default.
• W2890913619 hasConcept C103278499 @default.
• W2890913619 hasConcept C111919701 @default.
• W2890913619 hasConcept C115961682 @default.
• W2890913619 hasConcept C118505674 @default.
• W2890913619 hasConcept C125411270 @default.
• W2890913619 hasConcept C126388530 @default.
• W2890913619 hasConcept C138885662 @default.
• W2890913619 hasConcept C147168706 @default.
• W2890913619 hasConcept C154945302 @default.
• W2890913619 hasConcept C15744967 @default.
• W2890913619 hasConcept C204321447 @default.
• W2890913619 hasConcept C26517878 @default.
• W2890913619 hasConcept C2776401178 @default.
• W2890913619 hasConcept C28490314 @default.
• W2890913619 hasConcept C38652104 @default.
• W2890913619 hasConcept C41008148 @default.
• W2890913619 hasConcept C41895202 @default.
• W2890913619 hasConcept C50644808 @default.
• W2890913619 hasConcept C77805123 @default.
• W2890913619 hasConcept C81363708 @default.
• W2890913619 hasConceptScore W2890913619C103278499 @default.
• W2890913619 hasConceptScore W2890913619C111919701 @default.
• W2890913619 hasConceptScore W2890913619C115961682 @default.
• W2890913619 hasConceptScore W2890913619C118505674 @default.
• W2890913619 hasConceptScore W2890913619C125411270 @default.
• W2890913619 hasConceptScore W2890913619C126388530 @default.
• W2890913619 hasConceptScore W2890913619C138885662 @default.
• W2890913619 hasConceptScore W2890913619C147168706 @default.
• W2890913619 hasConceptScore W2890913619C154945302 @default.
• W2890913619 hasConceptScore W2890913619C15744967 @default.
• W2890913619 hasConceptScore W2890913619C204321447 @default.
• W2890913619 hasConceptScore W2890913619C26517878 @default.
• W2890913619 hasConceptScore W2890913619C2776401178 @default.
• W2890913619 hasConceptScore W2890913619C28490314 @default.
• W2890913619 hasConceptScore W2890913619C38652104 @default.
• W2890913619 hasConceptScore W2890913619C41008148 @default.
• W2890913619 hasConceptScore W2890913619C41895202 @default.
• W2890913619 hasConceptScore W2890913619C50644808 @default.
• W2890913619 hasConceptScore W2890913619C77805123 @default.
• W2890913619 hasConceptScore W2890913619C81363708 @default.
• W2890913619 hasFunder F4320306076 @default.
• W2890913619 hasIssue "2" @default.
• W2890913619 hasLocation W28909136191 @default.
• W2890913619 hasOpenAccess W2890913619 @default.
• W2890913619 hasPrimaryLocation W28909136191 @default.
• W2890913619 hasRelatedWork W2342046781 @default.
• W2890913619 hasRelatedWork W2547835662 @default.

• next