{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T21:41:18Z","timestamp":1788730878047,"version":"build-2803163510"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747336","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8867-8871","source":"Crossref","is-referenced-by-count":12,"title":["Unsupervised Audio-Caption Aligning Learns Correspondences Between Individual Sound Events and Textual Phrases"],"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":"Rasanen","sequence":"additional","affiliation":[{"name":"Tampere University,Unit of Computing Sciences,Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konstantinos","family":"Drossos","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01205-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-496"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414418"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414834"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref17","first-page":"1","article-title":"Learning hierarchical discrete linguistic units from visually-grounded speech","author":"harwath","year":"2020","journal-title":"Proc 8th Int Conf Learn Representations (ICLR)"},{"key":"ref18","first-page":"1","article-title":"Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques","author":"chrupa?a","year":"2021"},{"key":"ref19","first-page":"123","article-title":"Can phones, syllables, and words emerge as side-products of cross-situational audiovisual learning? — A computational investigation","volume":"1","author":"khorrami","year":"2021","journal-title":"Lang Dev Res"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3010650"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref5","first-page":"119","article-title":"AudioCaps: 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":"ref8","first-page":"1866","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682632"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/111"},{"key":"ref20","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc 1st Int Conf Learn Representations (ICLR)"},{"key":"ref21","article-title":"Word2Vec","year":"0"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747336.pdf?arnumber=9747336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:12Z","timestamp":1660593912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747336","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}