{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:17:23Z","timestamp":1740100643591,"version":"3.37.3"},"reference-count":28,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","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\/icassp43922.2022.9746601","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7892-7896","source":"Crossref","is-referenced-by-count":4,"title":["Joint Speech Recognition and Audio Captioning"],"prefix":"10.1109","author":[{"given":"Chaitanya","family":"Narisetty","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emiru","family":"Tsunoo","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yosuke","family":"Kashiwagi","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Hentschel","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2918706"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2757"},{"key":"ref12","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","author":"kim","year":"2019","journal-title":"Proc of NAACL-HLT"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref14","article-title":"Leveraging state-of-the-art ASR techniques to audio captioning","author":"narisetty","year":"2021","journal-title":"Tech Rep DCASE2016 Challenge"},{"article-title":"Audio captioning transformer","year":"2021","author":"mei","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1296","article-title":"Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM","author":"hori","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"article-title":"Sequence transduction with recurrent neural networks","year":"2012","author":"graves","key":"ref4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"ref3","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2014.80"},{"article-title":"Attention-based models for speech recognition","year":"2015","author":"chorowski","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"journal-title":"Automatic Speech Recognition","year":"2016","author":"yu","key":"ref1"},{"key":"ref20","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"2017","journal-title":"Proc of ICASSP"},{"article-title":"Serialized output training for end-to-end overlapped speech recognition","year":"2020","author":"kanda","key":"ref22"},{"key":"ref21","first-page":"6256","article-title":"End-to-end monaural multi-speaker ASR system without pre-training","author":"chang","year":"2019","journal-title":"Proc of ICASSP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref25","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"European Conference on Computer Vision"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09746601.pdf?arnumber=9746601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:34Z","timestamp":1661199094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746601","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}