{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:49:40Z","timestamp":1776880180779,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448085","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1456-1460","source":"Crossref","is-referenced-by-count":4,"title":["Audio Difference Learning for Audio Captioning"],"prefix":"10.1109","author":[{"given":"Tatsuya","family":"Komatsu","sequence":"first","affiliation":[{"name":"LINE Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Fujita","sequence":"additional","affiliation":[{"name":"LINE Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuya","family":"Takeda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682377"},{"key":"ref3","first-page":"211","article-title":"Audio captioning transformer","volume-title":"DCASE2021","author":"Mei","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00259-2"},{"key":"ref5","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref8","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL-HLT2019","author":"Kim"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref10","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. ICML2023","volume":"202","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","article-title":"Hyu submission for the dcase 2023 task 6a: automated audio captioning model using al-mixgen and synonyms substitution","author":"Cho","year":"2023"},{"key":"ref13","first-page":"161","article-title":"Advancing natural-language based audio retrieval with passt and large audio-caption data sets","volume-title":"Proc. DCASE2023","author":"Primus"},{"key":"ref14","article-title":"Beats-based audio captioning model with instructor embedding supervision and chatgpt mix-up","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Wu","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00042"},{"key":"ref16","author":"Kim","year":"2023","journal-title":"Exploring train and test-time augmentations for audio-language learning"},{"key":"ref17","first-page":"86","article-title":"Improving automated audio captioning fluency through data augmentation and ensemble selection","volume-title":"Proc. DCASE2023","author":"Kim"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097117"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1614"},{"key":"ref20","first-page":"206","article-title":"An encoder-decoder based audio captioning system with transfer and reinforcement learning","volume-title":"Proc. DCASE2021","author":"Mei"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref22","first-page":"201","article-title":"Audio-change captioning to explain machine-sound anomalies","volume-title":"Proc. DCASE2023","author":"Tsubaki"},{"key":"ref23","first-page":"191","article-title":"Audio difference captioning utilizing similarity-discrepancy disentanglement","volume-title":"Proc. DCASE2023","author":"Takeuchi"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448085.pdf?arnumber=10448085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:44:09Z","timestamp":1722581049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448085","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}