Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319862477> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4319862477 abstract "Data-driven speech processing models usually perform well with a large amount of text supervision, but collecting transcribed speech data is costly. Therefore, we propose Speech-CLIP, a novel framework bridging speech and text through images to enhance speech models without transcriptions. We leverage state-of-the-art pre-trained HuBERT and CLIP, aligning them via paired images and spoken captions with minimal fine-tuning. SpeechCLIP outperforms prior state-of-the-art on image-speech retrieval and performs zero-shot speech-text retrieval without direct supervision from transcriptions. Moreover, SpeechCLIP can directly retrieve semantically related keywords from speech." @default.
- W4319862477 created "2023-02-11" @default.
- W4319862477 creator A5004717608 @default.
- W4319862477 creator A5028858279 @default.
- W4319862477 creator A5040508737 @default.
- W4319862477 creator A5053466746 @default.
- W4319862477 creator A5078976109 @default.
- W4319862477 creator A5084236961 @default.
- W4319862477 date "2023-01-09" @default.
- W4319862477 modified "2023-09-24" @default.
- W4319862477 title "SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model" @default.
- W4319862477 cites W1905882502 @default.
- W4319862477 cites W2950133079 @default.
- W4319862477 cites W2962862718 @default.
- W4319862477 cites W2963330681 @default.
- W4319862477 cites W2963902314 @default.
- W4319862477 cites W2964099072 @default.
- W4319862477 cites W2972892814 @default.
- W4319862477 cites W2972943112 @default.
- W4319862477 cites W2973049979 @default.
- W4319862477 cites W2973135958 @default.
- W4319862477 cites W2982223350 @default.
- W4319862477 cites W2988907666 @default.
- W4319862477 cites W3015213852 @default.
- W4319862477 cites W3015300171 @default.
- W4319862477 cites W3041561163 @default.
- W4319862477 cites W3094626712 @default.
- W4319862477 cites W3097286738 @default.
- W4319862477 cites W3157861865 @default.
- W4319862477 cites W3161204797 @default.
- W4319862477 cites W3176445421 @default.
- W4319862477 cites W3189296823 @default.
- W4319862477 cites W3197467690 @default.
- W4319862477 cites W3197580070 @default.
- W4319862477 cites W3198858531 @default.
- W4319862477 cites W3200287550 @default.
- W4319862477 cites W3203140070 @default.
- W4319862477 cites W4224875474 @default.
- W4319862477 cites W4226033575 @default.
- W4319862477 cites W4284898017 @default.
- W4319862477 cites W4285250921 @default.
- W4319862477 cites W4286359908 @default.
- W4319862477 doi "https://doi.org/10.1109/slt54892.2023.10022954" @default.
- W4319862477 hasPublicationYear "2023" @default.
- W4319862477 type Work @default.
- W4319862477 citedByCount "0" @default.
- W4319862477 crossrefType "proceedings-article" @default.
- W4319862477 hasAuthorship W4319862477A5004717608 @default.
- W4319862477 hasAuthorship W4319862477A5028858279 @default.
- W4319862477 hasAuthorship W4319862477A5040508737 @default.
- W4319862477 hasAuthorship W4319862477A5053466746 @default.
- W4319862477 hasAuthorship W4319862477A5078976109 @default.
- W4319862477 hasAuthorship W4319862477A5084236961 @default.
- W4319862477 hasConcept C137293760 @default.
- W4319862477 hasConcept C14999030 @default.
- W4319862477 hasConcept C153083717 @default.
- W4319862477 hasConcept C154945302 @default.
- W4319862477 hasConcept C155635449 @default.
- W4319862477 hasConcept C174348530 @default.
- W4319862477 hasConcept C204201278 @default.
- W4319862477 hasConcept C204321447 @default.
- W4319862477 hasConcept C28490314 @default.
- W4319862477 hasConcept C31258907 @default.
- W4319862477 hasConcept C41008148 @default.
- W4319862477 hasConcept C54953205 @default.
- W4319862477 hasConcept C61328038 @default.
- W4319862477 hasConceptScore W4319862477C137293760 @default.
- W4319862477 hasConceptScore W4319862477C14999030 @default.
- W4319862477 hasConceptScore W4319862477C153083717 @default.
- W4319862477 hasConceptScore W4319862477C154945302 @default.
- W4319862477 hasConceptScore W4319862477C155635449 @default.
- W4319862477 hasConceptScore W4319862477C174348530 @default.
- W4319862477 hasConceptScore W4319862477C204201278 @default.
- W4319862477 hasConceptScore W4319862477C204321447 @default.
- W4319862477 hasConceptScore W4319862477C28490314 @default.
- W4319862477 hasConceptScore W4319862477C31258907 @default.
- W4319862477 hasConceptScore W4319862477C41008148 @default.
- W4319862477 hasConceptScore W4319862477C54953205 @default.
- W4319862477 hasConceptScore W4319862477C61328038 @default.
- W4319862477 hasFunder F4320307764 @default.
- W4319862477 hasFunder F4320309327 @default.
- W4319862477 hasFunder F4320316620 @default.
- W4319862477 hasLocation W43198624771 @default.
- W4319862477 hasOpenAccess W4319862477 @default.
- W4319862477 hasPrimaryLocation W43198624771 @default.
- W4319862477 hasRelatedWork W1501126083 @default.
- W4319862477 hasRelatedWork W1987021544 @default.
- W4319862477 hasRelatedWork W2376203252 @default.
- W4319862477 hasRelatedWork W2397833061 @default.
- W4319862477 hasRelatedWork W2535487273 @default.
- W4319862477 hasRelatedWork W3211053973 @default.
- W4319862477 hasRelatedWork W4319862477 @default.
- W4319862477 hasRelatedWork W642007152 @default.
- W4319862477 hasRelatedWork W82600882 @default.
- W4319862477 hasRelatedWork W2341426843 @default.
- W4319862477 isParatext "false" @default.
- W4319862477 isRetracted "false" @default.
- W4319862477 workType "article" @default.