{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:09:49Z","timestamp":1742954989845,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319491684"},{"type":"electronic","value":"9783319491691"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-49169-1_9","type":"book-chapter","created":{"date-parts":[[2016,11,3]],"date-time":"2016-11-03T11:31:46Z","timestamp":1478172706000},"page":"87-96","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Analysis of Deep Neural Networks in Broad Phonetic Classes for Noisy Speech Recognition"],"prefix":"10.1007","author":[{"given":"F.","family":"de-la-Calle-Silos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Gallardo-Antol\u00edn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Pel\u00e1ez-Moreno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,4]]},"reference":[{"key":"9_CR1","series-title":"Kluwer International Series in Engineering and Computer Science: VLSI, Computer Architecture, and Digital Signal Processing","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1","volume-title":"Connectionist Speech Recognition: A Hybrid Approach","author":"H Bourlard","year":"1994","unstructured":"Bourlard, H., Morgan, N.: Connectionist Speech Recognition: A Hybrid Approach. Kluwer International Series in Engineering and Computer Science: VLSI, Computer Architecture, and Digital Signal Processing. Springer, New York (1994)"},{"key":"9_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-319-13623-3_12","volume-title":"Advances in Speech and Language Technologies for Iberian Languages","author":"F de-la-Calle-Silos","year":"2014","unstructured":"de-la-Calle-Silos, F., Gallardo-Antol\u00edn, A., Pel\u00e1ez-Moreno, C.: Deep maxout networks applied to noise-robust speech recognition. In: Navarro Mesa, J.L., Ortega, A., Teixeira, A., Hern\u00e1ndez P\u00e9rez, E., Quintana Morales, P., Ravelo Garc\u00eda, A., Guerra Moreno, I., Toledano, D.T. (eds.) IberSPEECH 2014. LNCS (LNAI), vol. 8854, pp. 109\u2013118. Springer, Heidelberg (2014). doi:10.1007\/978-3-319-13623-3_12"},{"issue":"1","key":"9_CR3","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30\u201342 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"5","key":"9_CR4","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1109\/TASL.2006.878265","volume":"14","author":"L Deng","year":"2006","unstructured":"Deng, L., Yu, D., Acero, A.: Structured speech modeling. IEEE Trans. Audio Speech Lang. Process. 14(5), 1492\u20131504 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9_CR5","unstructured":"Fiscus, J.G.: A post-processing system to yield reduced word error rates: recognizer output voting error reduction (ROVER). In: Proceedings of 1997 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 347\u2013354, December 1997"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S., Dahlgren, N.L.: DARPA TIMIT acoustic phonetic continuous speech corpus CDROM (1993)","DOI":"10.6028\/NIST.IR.4930"},{"key":"9_CR7","unstructured":"Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. arXiv e-prints, February 2013"},{"key":"9_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/978-3-642-35289-8_32","volume-title":"Neural Networks: Tricks of the Trade","author":"GE Hinton","year":"2012","unstructured":"Hinton, G.E.: A practical guide to training restricted Boltzmann machines. In: Montavon, G., Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, 2nd edn, pp. 599\u2013619. Springer, Heidelberg (2012). doi:10.1007\/978-3-642-35289-8_32","edition":"2"},{"issue":"6","key":"9_CR9","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"GE Hinton","year":"2012","unstructured":"Hinton, G.E., Deng, L., Yu, D., Dahl, G.E., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sig. Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Sig. Process. Mag."},{"key":"9_CR10","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors. CoRR (2012)"},{"key":"9_CR11","unstructured":"Hirsch, G.: Fant - filtering and noise adding tool (2005). http:\/\/dnt.kr.hsnr.de\/download.html"},{"issue":"7","key":"9_CR12","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1109\/TASLP.2016.2545928","volume":"24","author":"C Kim","year":"2016","unstructured":"Kim, C., Stern, R.M.: Power-normalized cepstral coefficients (PNCC) for robust speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(7), 1315\u20131329 (2016). doi:10.1109\/TASLP.2016.2545928","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"4","key":"9_CR13","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TASLP.2014.2304637","volume":"22","author":"J Li","year":"2014","unstructured":"Li, J., Deng, L., Gong, Y., Haeb-Umbach, R.: An overview of noise-robust automatic speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(4), 745\u2013777 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"9_CR14","unstructured":"Miao, Y.: Kaldi+PDNN: building DNN-based ASR systems with Kaldi and PDNN. CoRR (2014)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Miao, Y., Metze, F., Rawat, S.: Deep maxout networks for low-resource speech recognition. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, 8\u201312 December 2013","DOI":"10.1109\/ASRU.2013.6707763"},{"issue":"1","key":"9_CR16","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","volume":"20","author":"A Mohamed","year":"2012","unstructured":"Mohamed, A., Dahl, G.E., Hinton, G.E.: Acoustic modeling using deep belief networks. IEEE Trans. Audio Speech Lang. Process. 20(1), 14\u201322 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"1","key":"9_CR17","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASL.2011.2116010","volume":"20","author":"N Morgan","year":"2012","unstructured":"Morgan, N.: Deep and wide: multiple layers in automatic speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 7\u201313 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"3","key":"9_CR18","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1121\/1.3458854","volume":"128","author":"C Pel\u00e1ez-Moreno","year":"2010","unstructured":"Pel\u00e1ez-Moreno, C., Garc\u00eda-Moral, A.I., Valverde-Albacete, F.J.: Analyzing phonetic confusions using formal concept analysis. J. Acoust. Soc. Am. 128(3), 1377\u20131390 (2010)","journal-title":"J. Acoust. Soc. Am."},{"key":"9_CR19","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society, December 2011"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Seltzer, M.L., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2013)","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"T\u00f3th, L.: Convolutional deep maxout networks for phone recognition. In: INTERSPEECH, pp. 1078\u20131082. ISCA (2014)","DOI":"10.21437\/Interspeech.2014-278"},{"key":"9_CR22","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371\u20133408 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR23","unstructured":"Wan, L., Zeiler, M.D., Zhang, S., LeCun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: Proceedings of 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16\u201321 June 2013"}],"container-title":["Lecture Notes in Computer Science","Advances in Speech and Language Technologies for Iberian Languages"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-49169-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T10:30:22Z","timestamp":1710325822000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-49169-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319491684","9783319491691"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-49169-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"4 November 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IberSPEECH","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advances in Speech and Language Technologies for Iberian Languages","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iberspeech2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iberspeech2016.inesc-id.pt\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}