{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T19:13:06Z","timestamp":1725477186443},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462578","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"6214-6218","source":"Crossref","is-referenced-by-count":1,"title":["An End-to-End Approach to Joint Social Signal Detection and Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Hirofumi","family":"Lnaguma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masato","family":"Mimura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koji","family":"Inoue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuyoshi","family":"Yoshii","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems","year":"2016","author":"martin","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472152"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref31"},{"key":"ref30","first-page":"1468","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref37","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proceedings of ICL"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref35","article-title":"Corpus of spontaneous japanese: Its design and evaluation","author":"maekawa","year":"2003","journal-title":"ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition"},{"key":"ref34","first-page":"212","article-title":"Talking with erica, an autonomous android","author":"inoue","year":"2016","journal-title":"Proceedings of SigDial"},{"key":"ref10","first-page":"2509","article-title":"Laugh-ter and filler detection in naturalistic audio","author":"kaushik","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854518"},{"key":"ref12","first-page":"2504","article-title":"On evaluation metrics for social signal detection","author":"gosztolya","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-457"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472710"},{"journal-title":"Deep speech 2 End-to-end speech recognition in english and mandarin","year":"2015","author":"amodei","key":"ref19"},{"key":"ref28","first-page":"362","article-title":"Hierarchical neural networks and enhanced class posteriors for social signal classification","author":"brueckner","year":"2013","journal-title":"Proceedings of ASRU"},{"key":"ref4","first-page":"163","article-title":"Detection of nonverbal vocalizations using gaussian mixture models: looking for fillers and laughter in conversational speech","author":"krikke","year":"2013","journal-title":"Proceedings of Interspeech"},{"key":"ref27","first-page":"148","article-title":"The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism","author":"schuller","year":"2013","journal-title":"Proceedings of Interspeech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-012-0092-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43958-7_27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878255"},{"key":"ref5","first-page":"153","article-title":"Non-linguistic vocalisation recognition based on hybrid GMM-SVM approach","author":"janicki","year":"2013","journal-title":"Proceedings of Interspeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2013.730"},{"key":"ref7","first-page":"220","article-title":"Detecting autism, emotions and social signals using adaboost","author":"gosztolya","year":"2013","journal-title":"Proceedings of Interspeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-012-0512-6"},{"key":"ref9","first-page":"173","article-title":"Paralinguistic event detection from speech using probabilistic time-series smoothing and masking","author":"gupta","year":"2013","journal-title":"Proceedings of INTER-SPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.11.007"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.1391244"},{"key":"ref22","first-page":"1958","article-title":"Acoustic features of four types of laughter in natural conversational speech","author":"tanaka","year":"2011","journal-title":"Proc Int Congress Phonetic Sciences"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/B:JONB.0000023654.73558.72"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-0277(02)00017-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1142\/9789812810687_0033"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1247"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-2166(99)00109-5"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462578.pdf?arnumber=8462578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T03:16:33Z","timestamp":1598238993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462578","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}