{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T12:10:02Z","timestamp":1748607002742,"version":"3.41.0"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319231310"},{"type":"electronic","value":"9783319231327"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-23132-7_37","type":"book-chapter","created":{"date-parts":[[2015,9,3]],"date-time":"2015-09-03T07:41:18Z","timestamp":1441266078000},"page":"301-308","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["On Deep and Shallow Neural Networks in Speech Recognition from Speech Spectrum"],"prefix":"10.1007","author":[{"given":"Jan","family":"Zelinka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petr","family":"Salajka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lud\u011bk","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,9,4]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Chang, S., Morgan, N.: Robust CNN-based speech recognition with Gabor filter kernels. In: 15th Annual Conference of the International Speech Communication Association (Interspeech 2014), pp. 905\u2013909, Singapore, September 14\u201318 (2014)","DOI":"10.21437\/Interspeech.2014-226"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Astudillo, R.F., Abad, A., Trancoso, I.: Accounting for the residual uncertainty of multi-layer perceptron based features. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6859\u20136863, May 2014","DOI":"10.1109\/ICASSP.2014.6854929"},{"key":"37_CR3","doi-asserted-by":"crossref","unstructured":"Gr\u00e9zl, F., Karafi\u00e1t, M.: Semi-supervised bootstrapping approach for neural network feature extractor training. In: ASRU, pp. 470\u2013475. IEEE (2013)","DOI":"10.1109\/ASRU.2013.6707775"},{"issue":"4","key":"37_CR4","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1121\/1.399423","volume":"57","author":"H He\u0159mansk\u00fd","year":"1990","unstructured":"He\u0159mansk\u00fd, H.: Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 57(4), 1738\u20131752 (1990)","journal-title":"J. Acoust. Soc. Am."},{"key":"37_CR5","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: CoRR abs\/1502.03167 (2015)"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Narayanan, A., Wang, D.: Ideal ratio mask estimation using deep neural networks for robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7092\u20137096, May 2013","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"37_CR7","unstructured":"Pra\u017e\u00e1k, A., Psutka, J.V., Psutka, J., Loose, Z.: Towards live subtitling of TV ice-hockey commentary. In: Cabello, E., Virvou, M., Obaidat, M.S., Ji, H., Nicopolitidis, P., Vergados, D.D. (eds.) SIGMAP, pp. 151\u2013155. SciTePress (2013)"},{"key":"37_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-642-15760-8_49","volume-title":"Text, Speech and Dialogue","author":"J Psutka","year":"2010","unstructured":"Psutka, J., \u0160vec, J., Psutka, J.V., Van\u011bk, J., Pra\u017e\u00e1k, A., \u0160m\u00eddl, L.: Fast phonetic\/lexical searching in\u00a0the archives of the czech holocaust testimonies: advancing towards the malach project visions. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2010. LNCS, vol. 6231, pp. 385\u2013391. Springer, Heidelberg (2010)"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Robinson, T., Fransen, J., Pye, D., Foote, J., Renals, S.: Wsjcam0: A british english speech corpus for large vocabulary continuous speech recognition. In: Proceedings of ICASSP 1995, pp. 81\u201384. IEEE (1995)","DOI":"10.1109\/ICASSP.1995.479278"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Mohamed, A.R., Ramabhadran, B.: Learning filter banks within a deep neural network framework. In: ASRU, pp. 297\u2013302. IEEE (2013)","DOI":"10.1109\/ASRU.2013.6707746"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Peddinti, V., Kingsbury, B., Fousek, P., Ramabhadran, B., Nahamoo, D.: Deep scattering spectra with deep neural networks for LVCSR tasks. In: 15th Annual Conference of the International Speech Communication Association (Interspeech 2014), pp. 900\u2013904, Singapore, September 14\u201318 (2014)","DOI":"10.21437\/Interspeech.2014-225"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Seps, L., M\u00e1lek, J., Cerva, P., Nouza, J.: Investigation of deep neural networks for robust recognition of nonlinearly distorted speech. In: Interspeech, pp. 363\u2013367 (2014)","DOI":"10.21437\/Interspeech.2014-85"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: CoRR abs\/1409.4842 (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"T\u00fcske, Z., Golik, P., Schl\u00fcter, R., Ney, H.: Acoustic modeling with deep neural networks using raw time signal for LVCSR. In: Interspeech, pp. 890\u2013894, Singapore, September 2014","DOI":"10.21437\/Interspeech.2014-223"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-23132-7_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T11:36:35Z","timestamp":1748604995000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-23132-7_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319231310","9783319231327"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-23132-7_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"4 September 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}