{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T09:59:47Z","timestamp":1760608787257,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1109\/asru.2013.6707757","type":"proceedings-article","created":{"date-parts":[[2014,1,10]],"date-time":"2014-01-10T15:07:23Z","timestamp":1389366443000},"page":"362-367","source":"Crossref","is-referenced-by-count":7,"title":["Hierarchical neural networks and enhanced class posteriors for social signal classification"],"prefix":"10.1109","author":[{"given":"Raymond","family":"Brueckner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bjorn","family":"Schuller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.21437\/Interspeech.2011-94","article-title":"Feature frame stacking in RNN-based tandem ASR systems - learned vs. Predefined context","author":"wo?llmer","year":"2011","journal-title":"Proc of Interspeech"},{"key":"17","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2023162"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.12-07-661"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"12","first-page":"3476","article-title":"Tandem connectionist feature extraction for conventional hmm systems","author":"hermansky","year":"2000","journal-title":"Proc of ICASSP"},{"key":"21","first-page":"1245","article-title":"Experiments on chinese speech recognition with tonal models and pitch estimation using the mandarin speecon data","author":"sun","year":"2006","journal-title":"Proc of Interspeech"},{"key":"20","first-page":"4176","article-title":"Error visualization for tandem acoustic modeling on the aurora task","author":"gomez","year":"2002","journal-title":"Proc of ICASSP"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"23","first-page":"833","article-title":"Contractive auto-encoders: Explicit invariance during feature extraction","author":"rifai","year":"2011","journal-title":"Proc of ICML"},{"key":"24","first-page":"148","article-title":"The interspeech 2013 computational paralinguistics challenge: Social signals, conflict, emotion, autism","author":"schuller","year":"2013","journal-title":"Proc of Interspeech"},{"key":"25","first-page":"105","article-title":"Time durations of phonemes in polish language for speech and speaker recognition","author":"zilko","year":"2009","journal-title":"LTC"},{"key":"26","first-page":"173","article-title":"Paralinguistic event detection from speech using probabilistic time-series smoothing and masking","author":"gupta","year":"2013","journal-title":"Proc of Interspeech"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706664"},{"key":"2","article-title":"Introduction to the special issue on next generation computational paralinguistics","author":"schuller","year":"2014","journal-title":"Computer Speech and Language Special Issue on Next Generation Computational Paralinguistics"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660050"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2192211"},{"key":"7","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-86","article-title":"The interspeech 2012 speaker trait challenge","author":"schuller","year":"2012","journal-title":"Proc of Interspeech"},{"key":"6","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-95","article-title":"Likability classification - A not so deep neural network approach","author":"brueckner","year":"2012","journal-title":"Proc of Interspeech"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34584-5_3"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639325"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947445"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947485"}],"event":{"name":"2013 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","start":{"date-parts":[[2013,12,8]]},"location":"Olomouc, Czech Republic","end":{"date-parts":[[2013,12,12]]}},"container-title":["2013 IEEE Workshop on Automatic Speech Recognition and Understanding"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6695806\/6707689\/06707757.pdf?arnumber=6707757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T21:04:05Z","timestamp":1647983045000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6707757\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru.2013.6707757","relation":{},"subject":[],"published":{"date-parts":[[2013,12]]}}}