{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T19:51:46Z","timestamp":1778356306933,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"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":[[2019,9]]},"DOI":"10.1109\/mmsp.2019.8901758","type":"proceedings-article","created":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T14:13:05Z","timestamp":1574691185000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Predicting Biological Signals from Speech: Introducing a Novel Multimodal Dataset and Results"],"prefix":"10.1109","author":[{"given":"Alice","family":"Baird","sequence":"first","affiliation":[{"name":"Augsburg University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shahin","family":"Amiriparian","sequence":"additional","affiliation":[{"name":"Augsburg University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miriam","family":"Berschneider","sequence":"additional","affiliation":[{"name":"Augsburg University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maximilian","family":"Schmitt","sequence":"additional","affiliation":[{"name":"Augsburg University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bj\u00f6rn","family":"Schuller","sequence":"additional","affiliation":[{"name":"Augsburg University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"0","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"ref32","first-page":"185","article-title":"12 fast training of support vector machines using sequential minimal optimization","author":"platt","year":"1999","journal-title":"Advances in Kernel Methods"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1656274.1656278"},{"key":"ref30","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"nitish","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1772"},{"key":"ref11","first-page":"3512","article-title":"Snore sound classification using image-based deep spectrum features","author":"amiriparian","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639064"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019533"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2018.8513102"},{"key":"ref15","article-title":"The biospeech database (bios-db) [data set]","author":"berschnider","year":"2019","journal-title":"Zenodo"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1159\/000119004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8260.1992.tb00997.x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/32\/10\/002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2016.2590178"},{"key":"ref28","article-title":"Sequence to sequence autoencoders for unsupervised representation learning from audio","author":"amiriparian","year":"0","journal-title":"Proc DCAS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195138108.003.0004"},{"key":"ref27","first-page":"1","article-title":"audeep: Unsupervised learning of representations from audio with deep recurrent neural networks","volume":"18","author":"freitag","year":"2018","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/1948550611430166"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/34.954607"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proceedings of the 3rd International Conference on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44566-8_3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/11608288_74"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0156339"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4324\/9781315795560"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref22","article-title":"Introducing the weighted trustability evaluator for crowdsourcing exemplified by speaker likability classification","author":"hantke","year":"2016","journal-title":"LREC"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854637"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"148","DOI":"10.21437\/Interspeech.2013-56","article-title":"The INTERSPEECH 2013 Computational Paralinguistics Challenge: Social Signals, Conflict, Emotion, Autism","author":"schuller","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref26","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25"},{"key":"ref25","first-page":"5","article-title":"Snore Sound Classification Using Image-based Deep Spectrum Features","author":"amiriparian","year":"2017","journal-title":"Proc of Interspeech"}],"event":{"name":"2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2019,9,27]]},"end":{"date-parts":[[2019,9,29]]}},"container-title":["2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8891847\/8901684\/08901758.pdf?arnumber=8901758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:41:19Z","timestamp":1755909679000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8901758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/mmsp.2019.8901758","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}