{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:39:12Z","timestamp":1783611552659,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,9,7]],"date-time":"2015-09-07T00:00:00Z","timestamp":1441584000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,9,7]]},"DOI":"10.1145\/2750858.2804262","type":"proceedings-article","created":{"date-parts":[[2015,9,15]],"date-time":"2015-09-15T12:27:44Z","timestamp":1442320064000},"page":"283-294","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":241,"title":["DeepEar"],"prefix":"10.1145","author":[{"given":"Nicholas D.","family":"Lane","sequence":"first","affiliation":[{"name":"Bell Labs"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petko","family":"Georgiev","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorena","family":"Qendro","sequence":"additional","affiliation":[{"name":"University of Bologna"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2015,9,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"British Library of Sounds. https:\/\/2.zoppoz.workers.dev:443\/http\/sounds.bl.uk\/.  British Library of Sounds. https:\/\/2.zoppoz.workers.dev:443\/http\/sounds.bl.uk\/."},{"key":"e_1_3_2_1_2_1","unstructured":"Free Sound Effects. https:\/\/2.zoppoz.workers.dev:443\/http\/www.freesfx.co.uk\/.  Free Sound Effects. https:\/\/2.zoppoz.workers.dev:443\/http\/www.freesfx.co.uk\/."},{"key":"e_1_3_2_1_3_1","unstructured":"LG G Watch R. https:\/\/2.zoppoz.workers.dev:443\/https\/www.qualcomm.com\/products\/snapdragon\/wearables\/lg-g-watch-r.  LG G Watch R. https:\/\/2.zoppoz.workers.dev:443\/https\/www.qualcomm.com\/products\/snapdragon\/wearables\/lg-g-watch-r."},{"key":"e_1_3_2_1_4_1","unstructured":"SoX. https:\/\/2.zoppoz.workers.dev:443\/http\/sox.sourceforge.net\/sox.html.  SoX. https:\/\/2.zoppoz.workers.dev:443\/http\/sox.sourceforge.net\/sox.html."},{"key":"e_1_3_2_1_5_1","unstructured":"Qualcomm Hexagon DSP. https:\/\/2.zoppoz.workers.dev:443\/https\/developer.qualcomm.com\/mobile-development\/maximize-hardware\/multimedia-optimization-hexagon-sdk\/hexagon-dsp-processor.  Qualcomm Hexagon DSP. https:\/\/2.zoppoz.workers.dev:443\/https\/developer.qualcomm.com\/mobile-development\/maximize-hardware\/multimedia-optimization-hexagon-sdk\/hexagon-dsp-processor."},{"key":"e_1_3_2_1_6_1","unstructured":"Qualcomm Snapdragon 400. https:\/\/2.zoppoz.workers.dev:443\/https\/www.qualcomm.com\/products\/snapdragon\/processors\/400.  Qualcomm Snapdragon 400. https:\/\/2.zoppoz.workers.dev:443\/https\/www.qualcomm.com\/products\/snapdragon\/processors\/400."},{"key":"e_1_3_2_1_7_1","unstructured":"Qualcomm Snapdragon MDP. https:\/\/2.zoppoz.workers.dev:443\/https\/developer.qualcomm.com\/mobile-development\/development-devices\/mobile-development-platform-mdp.  Qualcomm Snapdragon MDP. https:\/\/2.zoppoz.workers.dev:443\/https\/developer.qualcomm.com\/mobile-development\/development-devices\/mobile-development-platform-mdp."},{"key":"e_1_3_2_1_8_1","unstructured":"Theano Deep Learning. https:\/\/2.zoppoz.workers.dev:443\/http\/deeplearning.net\/software\/theano\/.  Theano Deep Learning. https:\/\/2.zoppoz.workers.dev:443\/http\/deeplearning.net\/software\/theano\/."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/11551201_4"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855085"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/1626431.1626476"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370216.2370289"},{"key":"e_1_3_2_1_13_1","volume-title":"Scaling Learning Algorithms Towards AI. Large-scale kernel machines, (34): 5","author":"Bengio Y.","year":"2007","unstructured":"Y. Bengio , Y. LeCun . Scaling Learning Algorithms Towards AI. Large-scale kernel machines, (34): 5 , 2007 . Y. Bengio, Y. LeCun. Scaling Learning Algorithms Towards AI. Large-scale kernel machines, (34): 5, 2007."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/1162264"},{"key":"e_1_3_2_1_15_1","first-page":"161","volume-title":"The Tradeoffs of Large Scale Learning. NIPS '08","author":"Bousquet O.","year":"2008","unstructured":"O. Bousquet , L. Bottou . The Tradeoffs of Large Scale Learning. NIPS '08 , pages 161 -- 168 , 2008 . O. Bousquet, L. Bottou. The Tradeoffs of Large Scale Learning. NIPS '08, pages 161--168, 2008."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460115"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493498"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"e_1_3_2_1_22_1","first-page":"1409","volume-title":"A. G. Fink Robust Time-synchronous Environmental Adaption for Continuous Speech Recognition Systems. Interspeech '02","author":"Pl\u00f6tz T.","year":"2002","unstructured":"T. Pl\u00f6tz , A. G. Fink Robust Time-synchronous Environmental Adaption for Continuous Speech Recognition Systems. Interspeech '02 , pages 1409 -- 1412 , 2002 . T. Pl\u00f6tz, A. G. Fink Robust Time-synchronous Environmental Adaption for Continuous Speech Recognition Systems. Interspeech '02, pages 1409--1412, 2002."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"e_1_3_2_1_24_1","unstructured":"J. Dean. Large Scale Deep Learning -- Research at Google. https:\/\/2.zoppoz.workers.dev:443\/http\/static.googleusercontent.com\/media\/research.google.com\/en\/\/people\/jeff\/CIKM-keynote-Nov2014.pdf.  J. Dean. Large Scale Deep Learning -- Research at Google. https:\/\/2.zoppoz.workers.dev:443\/http\/static.googleusercontent.com\/media\/research.google.com\/en\/\/people\/jeff\/CIKM-keynote-Nov2014.pdf."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1561\/2000000039"},{"key":"e_1_3_2_1_26_1","unstructured":"The Economist. Microphones As Sensors: Teaching Old Microphones New Tricks. https:\/\/2.zoppoz.workers.dev:443\/http\/www.economist.com\/news\/technology-quarterly\/21578518-sensor-technology-microphones-are-designed-capture-sound-they-turn-out.  The Economist. Microphones As Sensors: Teaching Old Microphones New Tricks. https:\/\/2.zoppoz.workers.dev:443\/http\/www.economist.com\/news\/technology-quarterly\/21578518-sensor-technology-microphones-are-designed-capture-sound-they-turn-out."},{"key":"e_1_3_2_1_27_1","first-page":"625","volume-title":"Journal of Machine Learning Research","author":"Erhan D.","year":"2010","unstructured":"D. Erhan , Y. Bengio , A. Courville , P.-A. Manzagol , P. Vincent , S. Bengio . Why Does Unsupervised Pre-training Help Deep Learning ? Journal of Machine Learning Research , pages 625 -- 660 , (11), 2010 . D. Erhan, Y. Bengio, A. Courville, P.-A. Manzagol, P. Vincent, S. Bengio. Why Does Unsupervised Pre-training Help Deep Learning? Journal of Machine Learning Research, pages 625--660, (11), 2010."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02943243"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/89.279278"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2668332.2668349"},{"key":"e_1_3_2_1_32_1","first-page":"557","volume-title":"Atlas. Acoustic Diversity for Improved Speech Recognition in Reverberant Environments. ICASSP '02","author":"Gillespie B. W.","unstructured":"B. W. Gillespie , L. E. Atlas. Acoustic Diversity for Improved Speech Recognition in Reverberant Environments. ICASSP '02 , pages I- 557 -- I-560, 2002. B. W. Gillespie, L. E. Atlas. Acoustic Diversity for Improved Speech Recognition in Reverberant Environments. ICASSP '02, pages I-557 -- I-560, 2002."},{"key":"e_1_3_2_1_33_1","first-page":"1764","volume-title":"Jaitly. Towards End-to-end Speech Recognition with Recurrent Neural Networks. ICML '14","author":"Graves A.","year":"2014","unstructured":"A. Graves , N. Jaitly. Towards End-to-end Speech Recognition with Recurrent Neural Networks. ICML '14 , pages 1764 -- 1772 , 2014 . A. Graves, N. Jaitly. Towards End-to-end Speech Recognition with Recurrent Neural Networks. ICML '14, pages 1764--1772, 2014."},{"key":"e_1_3_2_1_34_1","first-page":"6645","volume-title":"Speech Recognition with Deep Recurrent Neural Networks. ICASSP '13","author":"Graves A.","year":"2013","unstructured":"A. Graves , A.-R. Mohamed , G. Hinton . Speech Recognition with Deep Recurrent Neural Networks. ICASSP '13 , pages 6645 -- 6649 , 2013 . A. Graves, A.-R. Mohamed, G. Hinton. Speech Recognition with Deep Recurrent Neural Networks. ICASSP '13, pages 6645--6649, 2013."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9484"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-57"},{"key":"e_1_3_2_1_37_1","volume-title":"Deep Speech: Scaling up End-to-end Speech Recognition. arXiv preprint arXiv:1412.5567","author":"Hannun A. Y.","year":"2014","unstructured":"A. Y. Hannun , C. Case , J. Casper , B. C. Catanzaro , G. Diamos , E. Elsen , R. Prenger , S. Satheesh , S. Sengupta , A. Coates , A. Y. Ng . Deep Speech: Scaling up End-to-end Speech Recognition. arXiv preprint arXiv:1412.5567 ( 2014 ). A. Y. Hannun, C. Case, J. Casper, B. C. Catanzaro, G. Diamos, E. Elsen, R. Prenger, S. Satheesh, S. Sengupta, A. Coates, A. Y. Ng. Deep Speech: Scaling up End-to-end Speech Recognition. arXiv preprint arXiv:1412.5567 (2014)."},{"key":"e_1_3_2_1_38_1","first-page":"1738","volume-title":"Perceptual Linear Predictive (PLP) Analysis of Speech. Journal of the Acoustical Society of America","author":"Hermansky H.","year":"1990","unstructured":"H. Hermansky . Perceptual Linear Predictive (PLP) Analysis of Speech. Journal of the Acoustical Society of America , pages 1738 -- 1752 , (87): 4, 1990 . H. Hermansky. Perceptual Linear Predictive (PLP) Analysis of Speech. Journal of the Acoustical Society of America, pages 1738--1752, (87): 4, 1990."},{"key":"e_1_3_2_1_39_1","first-page":"599","volume-title":"Momentum","author":"Hinton G.","year":"2010","unstructured":"G. Hinton . A Practical Guide to Training Restricted Boltzmann Machines . Momentum , pages 599 -- 619 , (9): 1, 2010 . G. Hinton. A Practical Guide to Training Restricted Boltzmann Machines. Momentum, pages 599--619, (9): 1, 2010."},{"key":"e_1_3_2_1_40_1","first-page":"82","volume-title":"Signal Processing Magazine","author":"Hinton G.","year":"2012","unstructured":"G. Hinton , L. Deng , D. Yu , G. Dahl , A. rahman Mohamed , N. Jaitly , A. Senior , V. Vanhoucke , P. Nguyen , T. Sainath , B. Kingsbury . Deep Neural Networks for Acoustic Modeling in Speech Recognition . Signal Processing Magazine , pages 82 -- 97 , (29): 6, 2012 . G. Hinton, L. Deng, D. Yu, G. Dahl, A. rahman Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, B. Kingsbury. Deep Neural Networks for Acoustic Modeling in Speech Recognition. Signal Processing Magazine, pages 82--97, (29): 6, 2012."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-53"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"e_1_3_2_1_43_1","volume-title":"NIPS '14 -- Deep Learning Workshop","author":"Hinton G. E.","year":"2014","unstructured":"G. E. Hinton , O. Vinyals , J. Dean . Distilling the Knowledge in a Neural Network . NIPS '14 -- Deep Learning Workshop , 2014 . G. E. Hinton, O. Vinyals, J. Dean. Distilling the Knowledge in a Neural Network. NIPS '14 -- Deep Learning Workshop, 2014."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-214"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-013-0248-5"},{"key":"e_1_3_2_1_46_1","first-page":"1097","volume-title":"Imagenet Classification with Deep Convolutional Neural Networks. NIPS '12","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky , I. Sutskever , G. E. Hinton . Imagenet Classification with Deep Convolutional Neural Networks. NIPS '12 , pages 1097 -- 1105 , 2012 . A. Krizhevsky, I. Sutskever, G. E. Hinton. Imagenet Classification with Deep Convolutional Neural Networks. NIPS '12, pages 1097--1105, 2012."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2699343.2699349"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273556"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2030112.2030163"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2462456.2465426"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"e_1_3_2_1_52_1","first-page":"293","volume-title":"Musical Genre Classification of Audio Signals. Transactions on Speech and Audio Processing","author":"Li T.","year":"2002","unstructured":"T. Li . Musical Genre Classification of Audio Signals. Transactions on Speech and Audio Processing , pages 293 -- 302 , (10): 5, 2002 . T. Li. Musical Genre Classification of Audio Signals. Transactions on Speech and Audio Processing, pages 293--302, (10): 5, 2002."},{"key":"e_1_3_2_1_53_1","first-page":"S28","author":"Liberman M.","year":"2002","unstructured":"M. Liberman , K. Davis , M. Grossman , N. Martey , J. Bell. Emotional Prosody Speech and Transcripts. https:\/\/2.zoppoz.workers.dev:443\/https\/catalog.ldc.upenn.edu\/LDC 2002 S28 . M. Liberman, K. Davis, M. Grossman, N. Martey, J. Bell. Emotional Prosody Speech and Transcripts. https:\/\/2.zoppoz.workers.dev:443\/https\/catalog.ldc.upenn.edu\/LDC2002S28.","journal-title":"J. Bell. Emotional Prosody Speech and Transcripts. https:\/\/2.zoppoz.workers.dev:443\/https\/catalog.ldc.upenn.edu\/LDC"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/2021975.2021992"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370216.2370270"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555816.1555834"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/1814433.1814437"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/1460412.1460444"},{"key":"e_1_3_2_1_59_1","first-page":"185","volume-title":"ODYS-2004","author":"Fink A. G.","year":"2004","unstructured":"A. G. Fink , T. Pl\u00f6tz . Integrating Speaker Identification and Learning with Adaptive Speech Recognition . ODYS-2004 , pages 185 -- 192 , 2004 . A. G. Fink, T. Pl\u00f6tz. Integrating Speaker Identification and Learning with Adaptive Speech Recognition. ODYS-2004, pages 185--192, 2004."},{"key":"e_1_3_2_1_60_1","first-page":"807","volume-title":"Hinton. Rectified Linear Units Improve Restricted Boltzmann Machines. ICML '10","author":"Nair V.","year":"2010","unstructured":"V. Nair , G. E. Hinton. Rectified Linear Units Improve Restricted Boltzmann Machines. ICML '10 , pages 807 -- 814 , 2010 . V. Nair, G. E. Hinton. Rectified Linear Units Improve Restricted Boltzmann Machines. ICML '10, pages 807--814, 2010."},{"key":"e_1_3_2_1_61_1","author":"Park T. H.","year":"2014","unstructured":"T. H. Park , J. Turner , M. Musick , J. H. Lee , C. Jacoby , C. Mydlarz , J. Salamon. Sensing Urban Soundscapes. EDBT\/ICDT pages 375--382 , 2014 . T. H. Park, J. Turner, M. Musick, J. H. Lee, C. Jacoby, C. Mydlarz, J. Salamon. Sensing Urban Soundscapes. EDBT\/ICDT pages 375--382, 2014.","journal-title":"J. Salamon. Sensing Urban Soundscapes. EDBT\/ICDT pages 375--382"},{"key":"e_1_3_2_1_62_1","first-page":"1600","volume-title":"AAAI'10","author":"Peebles D.","year":"2010","unstructured":"D. Peebles , H. Lu , N. D. Lane , T. Choudhury , A. T. Campbell . Community-guided Learning : Exploiting Mobile Sensor Users to Model Human Behavior . AAAI'10 , pages 1600 -- 1606 , 2010 . D. Peebles, H. Lu, N. D. Lane, T. Choudhury, A. T. Campbell. Community-guided Learning: Exploiting Mobile Sensor Users to Model Human Behavior. AAAI'10, pages 1600--1606, 2010."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2030112.2030164"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1864349.1864393"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2594368.2594386"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/89.365379"},{"key":"e_1_3_2_1_67_1","first-page":"21","volume-title":"PhoneSense '10","author":"Miluzzo E.","year":"2010","unstructured":"E. Miluzzo , M. Papandrea , N. Lane , H. Lu , A. Campbell . Pocket, Bag, Hand, etc. -- Automatically Detecting Phone Context through Discovery . PhoneSense '10 , pages 21 -- 25 . 2010 . E. Miluzzo, M. Papandrea, N. Lane, H. Lu, A. Campbell. Pocket, Bag, Hand, etc. -- Automatically Detecting Phone Context through Discovery. PhoneSense '10, pages 21--25. 2010."},{"key":"e_1_3_2_1_68_1","first-page":"4330","volume-title":"Subspace Gaussian Mixture Models for Speech Recognition. ICASSP '10","author":"Povey D.","year":"2010","unstructured":"D. Povey , L. Burget , M. Agarwal , P. Akyazi , F. Kai , A. Ghoshal , O. Glembek , N. Goel , M. Karafiat , A. Rastrow , R. Rose , P. Schwarz , S. Thomas . Subspace Gaussian Mixture Models for Speech Recognition. ICASSP '10 , pages 4330 -- 4333 , 2010 . D. Povey, L. Burget, M. Agarwal, P. Akyazi, F. Kai, A. Ghoshal, O. Glembek, N. Goel, M. Karafiat, A. Rastrow, R. Rose, P. Schwarz, S. Thomas. Subspace Gaussian Mixture Models for Speech Recognition. ICASSP '10, pages 4330--4333, 2010."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"e_1_3_2_1_70_1","first-page":"7398","volume-title":"An Investigation of Deep Neural Networks for Noise Robust Speech Recognition. ICASSP '13","author":"Seltzer M. L.","year":"2013","unstructured":"M. L. Seltzer , D. Yu , Y. Wang . An Investigation of Deep Neural Networks for Noise Robust Speech Recognition. ICASSP '13 , pages 7398 -- 7402 . 2013 . M. L. Seltzer, D. Yu, Y. Wang. An Investigation of Deep Neural Networks for Noise Robust Speech Recognition. ICASSP '13, pages 7398--7402. 2013."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/2525526.2525856"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/1869983.1869992"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517351.2517362"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/2030112.2030160"},{"key":"e_1_3_2_1_75_1","first-page":"4052","volume-title":"J. Gonzalez-Dominguez. Deep Neural Networks for Small Footprint Text-dependent Speaker Verification. ICASSP '14","author":"Variani E.","year":"2014","unstructured":"E. Variani , X. Lei , E. McDermott , I. L. Moreno , J. Gonzalez-Dominguez. Deep Neural Networks for Small Footprint Text-dependent Speaker Verification. ICASSP '14 , pages 4052 -- 4056 , 2014 . E. Variani, X. Lei, E. McDermott, I. L. Moreno, J. Gonzalez-Dominguez. Deep Neural Networks for Small Footprint Text-dependent Speaker Verification. ICASSP '14, pages 4052--4056, 2014."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/2566486.2568027"},{"key":"e_1_3_2_1_77_1","first-page":"1481","volume-title":"NIPS '04","author":"Welling M.","year":"2004","unstructured":"M. Welling , M. Rosen-Zvi , G. E. Hinton . Exponential Family Harmoniums with an Application to Information Retrieval . NIPS '04 , pages 1481 -- 1488 , 2004 . M. Welling, M. Rosen-Zvi, G. E. Hinton. Exponential Family Harmoniums with an Application to Information Retrieval. NIPS '04, pages 1481--1488, 2004."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493435"}],"event":{"name":"UbiComp '15: The 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing","location":"Osaka Japan","acronym":"UbiComp '15","sponsor":["Yahoo! Japan Yahoo! Japan","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","FX Palo Alto Laboratory, Inc. FX Palo Alto Laboratory, Inc.","Google Inc.","ACM Association for Computing Machinery","Rakuten Institute of Technology Rakuten Institute of Technology","Microsoft Microsoft","Bell Labs Bell Laboratories","SIGCHI ACM Special Interest Group on Computer-Human Interaction","KDDI"]},"container-title":["Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/2750858.2804262","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/2750858.2804262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:00:42Z","timestamp":1750230042000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/2750858.2804262"}},"subtitle":["robust smartphone audio sensing in unconstrained acoustic environments using deep learning"],"short-title":[],"issued":{"date-parts":[[2015,9,7]]},"references-count":78,"alternative-id":["10.1145\/2750858.2804262","10.1145\/2750858"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/2750858.2804262","relation":{},"subject":[],"published":{"date-parts":[[2015,9,7]]},"assertion":[{"value":"2015-09-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}