{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:10:14Z","timestamp":1784146214840,"version":"3.55.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2013,12,1]],"date-time":"2013-12-01T00:00:00Z","timestamp":1385856000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2013,12,1]],"date-time":"2013-12-01T00:00:00Z","timestamp":1385856000000},"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":[[2013,12]]},"DOI":"10.1109\/asru.2013.6707754","type":"proceedings-article","created":{"date-parts":[[2014,1,10]],"date-time":"2014-01-10T15:07:23Z","timestamp":1389366443000},"page":"344-349","source":"Crossref","is-referenced-by-count":6,"title":["DNN acoustic modeling with modular multi-lingual feature extraction networks"],"prefix":"10.1109","author":[{"given":"Jonas","family":"Gehring","sequence":"first","affiliation":[{"name":"Interactive Systems Lab, Karlsruhe Institute of Technology; Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quoc Bao","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Interactive Systems Lab, Karlsruhe Institute of Technology; Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Waibel","sequence":"additional","affiliation":[{"name":"Interactive Systems Lab, Karlsruhe Institute of Technology; Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"crossref","first-page":"2711","DOI":"10.21437\/Interspeech.2008-672","article-title":"On the use of a multilingual neural network front-end","author":"scanzio","year":"2008","journal-title":"Proc 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":"The Journal of Machine Learning Research"},{"key":"18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-12","article-title":"An investigation on initialization schemes for multilayer perceptron training using multilingual data and their effect on asr performance","author":"vu","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638284"},{"key":"16","first-page":"153","article-title":"Greedy layer-wise training of deep networks","volume":"19","author":"bengio","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424230"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367023"},{"key":"11","doi-asserted-by":"crossref","first-page":"2963","DOI":"10.21437\/Interspeech.2009-750","article-title":"Hierarchical processing of the modulation spectrum for gale mandarin lvcsr system","author":"valente","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"12","article-title":"Modular combination of deep neural networks for acoustic modeling","author":"gehring","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639017"},{"key":"20","article-title":"Roles of pre-training and finetuning in context-dependent dbn-hmms for real-world speech recognition","author":"yu","year":"2010","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639084"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1121\/1.2934193"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707740"},{"key":"25","year":"0","journal-title":"IARPA Office for Incisive Analysis Babel Program"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599552"},{"key":"27","doi-asserted-by":"crossref","DOI":"10.25080\/Majora-92bf1922-003","article-title":"Theano: A CPU and GPU math expression compiler","author":"bergstra","year":"2010","journal-title":"Proceedings of the Python for Scientific Computing Conference (SciPy)"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424210"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.1.1"},{"key":"10","article-title":"Dataderived nonlinear mapping for feature extraction in hmm","volume":"99","author":"hermansky","year":"1999","journal-title":"Proc ASRU"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"},{"key":"6","doi-asserted-by":"crossref","first-page":"437","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"4","first-page":"135","article-title":"Multi-state time delay neural networks for continuous speech recognition","author":"haffner","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/29.45535"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639348"}],"event":{"name":"2013 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","location":"Olomouc, Czech Republic","start":{"date-parts":[[2013,12,8]]},"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\/06707754.pdf?arnumber=6707754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:02:28Z","timestamp":1784145748000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6707754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/asru.2013.6707754","relation":{},"subject":[],"published":{"date-parts":[[2013,12]]}}}