{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T04:10:48Z","timestamp":1748751048361,"version":"3.41.0"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319257884"},{"type":"electronic","value":"9783319257891"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-25789-1_27","type":"book-chapter","created":{"date-parts":[[2015,11,16]],"date-time":"2015-11-16T15:03:59Z","timestamp":1447686239000},"page":"288-299","source":"Crossref","is-referenced-by-count":2,"title":["Neural-Network-Based Spectrum Processing for Speech Recognition and Speaker Verification"],"prefix":"10.1007","author":[{"given":"Jan","family":"Zelinka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Van\u011bk","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":[[2015,11,17]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Chang, S., Morgan, N.: Robust CNN-based speech recognition with Gabor filter kernels. In: Interspeech 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, 14\u201318 September 2014, pp. 905\u2013909 (2014)","DOI":"10.21437\/Interspeech.2014-226"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Das, A., Tapaswi, M.: Direct modeling of spoken passwords for text-dependent speaker recognition by compressed time-feature representations. In: ICASSP, IEEE, March 2010","DOI":"10.1109\/ICASSP.2010.5495588"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Astudillo, R.F., Abad, A., Trancoso, I.: Accounting for the residual uncertainty of multi-layer perceptron based features. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6859\u20136863, May 2014","DOI":"10.1109\/ICASSP.2014.6854929"},{"key":"27_CR4","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"},{"key":"27_CR5","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1007\/978-3-540-49127-9_37","volume-title":"Springer Handbook of Speech Processing","author":"M Hbert","year":"2008","unstructured":"Hbert, M.: Text-dependent speaker recognition. In: Benesty, J., Sondhi, M., Huang, Y. (eds.) Springer Handbook of Speech Processing, pp. 743\u2013762. Springer, Berlin Heidelberg (2008)"},{"issue":"4","key":"27_CR6","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":"27_CR7","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR abs\/1502.03167 (2015)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Narayanan, A., Wang, D.: Ideal ratio mask estimation using deep neural networks for robust speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7092\u20137096, May 2013","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"27_CR9","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":"27_CR10","doi-asserted-by":"crossref","unstructured":"Ramasubramanian, V., Das, A., Praveen, K.V.: Text-dependent speaker-recognition using one-pass dynamic programming algorithm. In: 2006 IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP 2006, Toulouse, France, 14\u201319 May 2006, pp. 901\u2013904 (2006)","DOI":"10.1109\/ICASSP.2006.1660167"},{"key":"27_CR11","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":"27_CR12","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Rahman Mohamed, A., 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":"27_CR13","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: Interspeech 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, 14\u201318 September 2014, pp. 900\u2013904 (2014)","DOI":"10.1109\/ICASSP.2014.6853588"},{"key":"27_CR14","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"},{"issue":"1","key":"27_CR15","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., 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":"27_CR16","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. CoRR abs\/1409.4842 (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"27_CR17","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, Singapore, pp. 890\u2013894. September 2014","DOI":"10.21437\/Interspeech.2014-223"},{"issue":"4","key":"27_CR18","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1109\/TSA.2005.848892","volume":"13","author":"B Yegnanarayana","year":"2005","unstructured":"Yegnanarayana, B., Prasanna, S., Zachariah, J., Gupta, C.: Combining evidence from source, suprasegmental and spectral features for a fixed-text speaker verification system. IEEE Trans. Speech Audio Process. 13(4), 575\u2013582 (2005)","journal-title":"IEEE Trans. Speech Audio Process."}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-25789-1_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T12:07:39Z","timestamp":1748693259000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-25789-1_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319257884","9783319257891"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-25789-1_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]}}}