{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:56:08Z","timestamp":1764399368731,"version":"3.46.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249388","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"682-687","source":"Crossref","is-referenced-by-count":0,"title":["Effectiveness of Streaming ASR for Real-Time Laughter and Screaming Detection"],"prefix":"10.1109","author":[{"given":"Mizuki","family":"Kurasawa","sequence":"first","affiliation":[{"name":"Chiba Institute of Technology,Chiba,Japan"}]},{"given":"Yoshiko","family":"Arimoto","sequence":"additional","affiliation":[{"name":"Chiba Institute of Technology,Chiba,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.11.007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2024-135"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/j.0963-7214.2004.00311.x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/Indo-TaiwanICAN48429.2020.9181340"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-281"},{"key":"ref6","article-title":"Automatic speech recognition model simultaneously recognizes linguistic information and verbal\/non-verbal phenomena","author":"Shione","year":"2023","journal-title":"Proc. 2023 Autumn Meeting Acoustical Society of Japan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-457"},{"issue":"1","key":"ref8","first-page":"19","article-title":"Laughter and screaming detection utilizing automatic apeech recognition using wav2vec 2.0","volume":"4","author":"Matsuda","year":"2024","journal-title":"Proc. the Speech Processing Meeting The Acoustical Society of Japan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-353"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-541"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.28"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iciea.2010.5515397"},{"key":"ref13","first-page":"1216","article-title":"Scream and gunshot detection in noisy environments","author":"Gerosa","year":"2007","journal-title":"Proc, EUSIPCO"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1412"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383517"},{"key":"ref16","first-page":"83","article-title":"Double decoder: Improving latency for streaming end-to-end ASR models","author":"Wang","year":"2024","journal-title":"Proc. the ICNLSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11216"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096378"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref21","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Baevski","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2553"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1250\/ast.33.359"},{"key":"ref24","first-page":"92","article-title":"Effects of reactions generated by a virtual world on game players under laughing\/non-laughing conditions","volume":"97","author":"Fukuda","year":"2023","journal-title":"Proc. SIG-SLUD, JSAI"},{"key":"ref25","first-page":"MMO2","article-title":"Corpus of Spontaneous Japanese: Its design and evaluation","author":"Maekawa","year":"2003","journal-title":"Proc. ISCA\/ IEEE Workshop on Spontaneous Speech Processing and Recognition"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2131"},{"key":"ref27","first-page":"365","article-title":"Scream and shout annotation for spontaneous dialog speech","volume":"1","author":"Shiratori","year":"2023","journal-title":"Proc. Language Resources Workshop"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.4979337"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249388.pdf?arnumber=11249388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:07Z","timestamp":1764399067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249388\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249388","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}