Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210913346> ?p ?o ?g. }
- W4210913346 endingPage "2685" @default.
- W4210913346 startingPage "2675" @default.
- W4210913346 abstract "The objectives of this work are cross-modal text-audio and audio-text retrieval, in which the goal is to retrieve the audio content from a pool of candidates that best matches a given written description and vice versa. Text-audio retrieval enables users to search large databases through an intuitive interface: they simply issue free-form natural language descriptions of the sound they would like to hear. To study the tasks of text-audio and audio-text retrieval, which have received limited attention in the existing literature, we introduce three challenging new benchmarks. We first construct text-audio and audio-text retrieval benchmarks from the AudioCaps and Clotho audio captioning datasets. Additionally, we introduce the SoundDescs benchmark, which consists of paired audio and natural language descriptions for a diverse collection of sounds that are complementary to those found in AudioCaps and Clotho. We employ these three benchmarks to establish baselines for cross-modal text-audio and audio-text retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into audio retrieval with free-form text queries. Code, audio features for all datasets used, and the SoundDescs dataset are publicly available at https://github.com/akoepke/audio-retrieval-benchmark." @default.
- W4210913346 created "2022-02-09" @default.
- W4210913346 creator A5001366802 @default.
- W4210913346 creator A5036345396 @default.
- W4210913346 creator A5040372929 @default.
- W4210913346 creator A5084478386 @default.
- W4210913346 creator A5090528235 @default.
- W4210913346 date "2023-01-01" @default.
- W4210913346 modified "2023-10-03" @default.
- W4210913346 title "Audio Retrieval With Natural Language Queries: A Benchmark Study" @default.
- W4210913346 cites W1600745603 @default.
- W4210913346 cites W2010486494 @default.
- W4210913346 cites W2033875152 @default.
- W4210913346 cites W2046955072 @default.
- W4210913346 cites W2048174296 @default.
- W4210913346 cites W2052666245 @default.
- W4210913346 cites W2074188409 @default.
- W4210913346 cites W2086384421 @default.
- W4210913346 cites W2101305062 @default.
- W4210913346 cites W2103279261 @default.
- W4210913346 cites W2108598243 @default.
- W4210913346 cites W2111331420 @default.
- W4210913346 cites W2112861900 @default.
- W4210913346 cites W2139501017 @default.
- W4210913346 cites W2149557440 @default.
- W4210913346 cites W2176625348 @default.
- W4210913346 cites W2425121537 @default.
- W4210913346 cites W2526050071 @default.
- W4210913346 cites W2593116425 @default.
- W4210913346 cites W2732026016 @default.
- W4210913346 cites W2739107216 @default.
- W4210913346 cites W2808399042 @default.
- W4210913346 cites W2889650715 @default.
- W4210913346 cites W2916103538 @default.
- W4210913346 cites W2940092410 @default.
- W4210913346 cites W2951019013 @default.
- W4210913346 cites W2962968152 @default.
- W4210913346 cites W2963022469 @default.
- W4210913346 cites W2963155035 @default.
- W4210913346 cites W2963446712 @default.
- W4210913346 cites W2963507712 @default.
- W4210913346 cites W2963703197 @default.
- W4210913346 cites W2963801643 @default.
- W4210913346 cites W2963902314 @default.
- W4210913346 cites W2963916161 @default.
- W4210913346 cites W2964213897 @default.
- W4210913346 cites W2964287480 @default.
- W4210913346 cites W2964891022 @default.
- W4210913346 cites W2972073579 @default.
- W4210913346 cites W2973109987 @default.
- W4210913346 cites W2980037812 @default.
- W4210913346 cites W2982343573 @default.
- W4210913346 cites W3015371781 @default.
- W4210913346 cites W3015591594 @default.
- W4210913346 cites W3041053424 @default.
- W4210913346 cites W3094550259 @default.
- W4210913346 cites W3095941556 @default.
- W4210913346 cites W3102887392 @default.
- W4210913346 cites W3122335742 @default.
- W4210913346 cites W3133481345 @default.
- W4210913346 cites W3153005511 @default.
- W4210913346 cites W3160577380 @default.
- W4210913346 cites W3161945002 @default.
- W4210913346 cites W3163843406 @default.
- W4210913346 cites W3198452188 @default.
- W4210913346 cites W3204588463 @default.
- W4210913346 cites W877909479 @default.
- W4210913346 doi "https://doi.org/10.1109/tmm.2022.3149712" @default.
- W4210913346 hasPublicationYear "2023" @default.
- W4210913346 type Work @default.
- W4210913346 citedByCount "6" @default.
- W4210913346 countsByYear W42109133462022 @default.
- W4210913346 countsByYear W42109133462023 @default.
- W4210913346 crossrefType "journal-article" @default.
- W4210913346 hasAuthorship W4210913346A5001366802 @default.
- W4210913346 hasAuthorship W4210913346A5036345396 @default.
- W4210913346 hasAuthorship W4210913346A5040372929 @default.
- W4210913346 hasAuthorship W4210913346A5084478386 @default.
- W4210913346 hasAuthorship W4210913346A5090528235 @default.
- W4210913346 hasBestOaLocation W42109133462 @default.
- W4210913346 hasConcept C115961682 @default.
- W4210913346 hasConcept C13280743 @default.
- W4210913346 hasConcept C154945302 @default.
- W4210913346 hasConcept C155635449 @default.
- W4210913346 hasConcept C157657479 @default.
- W4210913346 hasConcept C157968479 @default.
- W4210913346 hasConcept C185798385 @default.
- W4210913346 hasConcept C195324797 @default.
- W4210913346 hasConcept C199360897 @default.
- W4210913346 hasConcept C204321447 @default.
- W4210913346 hasConcept C205649164 @default.
- W4210913346 hasConcept C23123220 @default.
- W4210913346 hasConcept C2780801425 @default.
- W4210913346 hasConcept C28490314 @default.
- W4210913346 hasConcept C41008148 @default.
- W4210913346 hasConcept C61328038 @default.
- W4210913346 hasConceptScore W4210913346C115961682 @default.
- W4210913346 hasConceptScore W4210913346C13280743 @default.