{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:12:22Z","timestamp":1775196742527,"version":"3.50.1"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030007935","type":"print"},{"value":"9783030007942","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-00794-2_47","type":"book-chapter","created":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T19:50:24Z","timestamp":1536349824000},"page":"436-444","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["A Survey of Recent DNN Architectures on the TIMIT Phone Recognition Task"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7757-3163","authenticated-orcid":false,"given":"Josef","family":"Mich\u00e1lek","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2639-6731","authenticated-orcid":false,"given":"Jan","family":"Van\u011bk","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,9,8]]},"reference":[{"key":"47_CR1","unstructured":"A flexible framework of neural networks for deep learning. https:\/\/chainer.org"},{"key":"47_CR2","unstructured":"Garofolo, J.S., et al.: TIMIT Acoustic-Phonetic Continuous Speech Corpus. Linguistic Data Consortium LDC93S1 (1993)"},{"issue":"7","key":"47_CR3","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527\u20131554 (2006)","journal-title":"Neural Comput."},{"issue":"8","key":"47_CR4","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"47_CR5","unstructured":"Kaldi speech recognition toolkit. https:\/\/github.com\/kaldi-asr\/kaldi"},{"issue":"Jan","key":"47_CR6","first-page":"1","volume":"10","author":"H Larochelle","year":"2009","unstructured":"Larochelle, H., Bengio, Y., Louradour, J., Lamblin, P.: Exploring strategies for training deep neural networks. J. Mach. Learn. Res. 10(Jan), 1\u201340 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"47_CR7","doi-asserted-by":"publisher","DOI":"10.5772\/17600","volume-title":"Speech Technologies","author":"Carla Lopes","year":"2011","unstructured":"Lopes, C., Perdigao, F.: Phoneme Recognition on the TIMIT Database. Speech Technologies (2011). https:\/\/doi.org\/10.5772\/17600, http:\/\/www.intechopen.com\/books\/speech-technologies\/phoneme-recognition-on-the-timit-database"},{"issue":"1","key":"47_CR8","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.: Acoustic modeling using deep belief networks. IEEE Trans. Audio Speech Lang. Process. 20(1), 14\u201322 (2012). https:\/\/doi.org\/10.1109\/TASL.2011.2109382","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"47_CR9","doi-asserted-by":"crossref","unstructured":"Moon, T., Choi, H., Lee, H., Song, I.: RNNDROP: a novel dropout for RNNs in ASR. In: Proceedings of the ASRU (2015)","DOI":"10.1109\/ASRU.2015.7404775"},{"key":"47_CR10","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-647"},{"issue":"1","key":"47_CR11","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"47_CR12","doi-asserted-by":"crossref","unstructured":"T\u00f3th, L.: Convolutional deep rectifier neural nets for phone recognition. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 1722\u20131726, August 2013","DOI":"10.21437\/Interspeech.2013-429"},{"key":"47_CR13","doi-asserted-by":"publisher","unstructured":"T\u00f3th, L.: Convolutional deep maxout networks for phone recognition. In: Proceedings of the INTERSPEECH, pp. 1078\u20131082 (2014). https:\/\/doi.org\/10.1186\/s13636-015-0068-3","DOI":"10.1186\/s13636-015-0068-3"},{"key":"47_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/978-3-319-68456-7_17","volume-title":"Statistical Language and Speech Processing","author":"J Van\u011bk","year":"2017","unstructured":"Van\u011bk, J., Zelinka, J., Soutner, D., Psutka, J.: A regularization post layer: an additional way how to make deep neural networks robust. In: Camelin, N., Est\u00e8ve, Y., Mart\u00edn-Vide, C. (eds.) SLSP 2017. LNCS (LNAI), vol. 10583, pp. 204\u2013214. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-68456-7_17"},{"key":"47_CR15","doi-asserted-by":"crossref","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.J.: Phoneme recognition using time-delay neural networks. In: Readings in Speech Recognition, pp. 393\u2013404. Elsevier (1990)","DOI":"10.1016\/B978-0-08-051584-7.50037-1"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00794-2_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:38:13Z","timestamp":1709829493000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00794-2_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007935","9783030007942"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00794-2_47","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"8 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}