{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:14:16Z","timestamp":1787012056474,"version":"build-2736575974"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095319","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["On Negative Sampling for Contrastive Audio-Text Retrieval"],"prefix":"10.1109","author":[{"given":"Huang","family":"Xie","sequence":"first","affiliation":[{"name":"Tampere University,Unit of Computing Sciences,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Okko","family":"R\u00e4s\u00e4nen","sequence":"additional","affiliation":[{"name":"Tampere University,Unit of Computing Sciences,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[{"name":"Tampere University,Unit of Computing Sciences,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref12","article-title":"Audio Retrieval with WavText5K and CLAP Training","author":"deshmukh","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"ref15","article-title":"CLAP: Learning Audio Concepts from Natural Language Supervision","author":"elizalde","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref22","article-title":"Word2Vec","year":"0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref21","first-page":"225","article-title":"A CRNN-GRU Based Reinforcement Learning Approach to Audio Captioning","author":"xu","year":"2019","journal-title":"Proc Detect Classif Acoust Scenes Events Work (DCASE)"},{"key":"ref2","first-page":"iv-4108","article-title":"Semantic-Audio Retrieval","author":"slaney","year":"2002","journal-title":"Proc Int Conf Acoustic Speech and Signal Process (ICASSP)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747336"},{"key":"ref17","first-page":"1","article-title":"Contrastive Learning with Hard Negative Samples","author":"robinson","year":"2021","journal-title":"Proc Int Conf Learn Representations (ICLR)"},{"key":"ref16","article-title":"Language-based Audio Retrieval Task in DCASE 2022 Challenge","author":"xie","year":"2022"},{"key":"ref19","first-page":"1101","article-title":"Do More Negative Samples Necessarily Hurt In Contrastive Learning?","author":"awasthi","year":"2022","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref18","article-title":"Negative Sampling for Contrastive Representation Learning: A Review","author":"xu","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2227"},{"key":"ref7","first-page":"119","article-title":"Audio-Caps: Generating Captions for Audios in The Wild","author":"kim","year":"2019","journal-title":"Proc Conf North Am Chapter Assoc Comput Linguist Hum Lang Technol (HLT-NAACL)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11115"},{"key":"ref4","first-page":"59","article-title":"Acoustic event search with an onomatopoeic query: measuring distance between onomatopoeic words and sounds","author":"ikawa","year":"2018","journal-title":"Proc Detect Classif Acoust Scenes Events Work (DCASE)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460115"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682632"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095319.pdf?arnumber=10095319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:58:35Z","timestamp":1699883915000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095319","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}