{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T21:45:23Z","timestamp":1725745523834},"publisher-location":"Berlin, Heidelberg","reference-count":26,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642405846"},{"type":"electronic","value":"9783642405853"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40585-3_2","type":"book-chapter","created":{"date-parts":[[2013,8,17]],"date-time":"2013-08-17T10:15:02Z","timestamp":1376734502000},"page":"14-21","source":"Crossref","is-referenced-by-count":0,"title":["Long, Deep and Wide Artificial Neural Nets for Dealing with Unexpected Noise in Machine Recognition of\u00a0Speech"],"prefix":"10.1007","author":[{"given":"Hynek","family":"Hermansky","sequence":"first","affiliation":[]}],"member":"297","reference":[{"issue":"12","key":"2_CR1","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1109\/34.62605","volume":"12","author":"H. Bourlard","year":"1990","unstructured":"Bourlard, H., Wellekens, C.J.: Links between markov models and multilayer perceptrons. IEEE Trans. Patt. Anal. and Machine Intell.\u00a012(12), 1167\u20131178 (1990)","journal-title":"IEEE Trans. Patt. Anal. and Machine Intell."},{"doi-asserted-by":"crossref","unstructured":"Seide, F., Li, G., Yu, D.: Conversational speech transcription using context-dependent deep neural networks. In: Proc. Interspeech, pp. 437\u2013412 (2011)","key":"2_CR2","DOI":"10.21437\/Interspeech.2011-169"},{"issue":"1","key":"2_CR3","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 Transactions on Audio, Speech, and Language Processing\u00a020(1), 7\u201313 (2012)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"unstructured":"Miller, G.: Language and Communication. McGraw-Hill Book Company (1951)","key":"2_CR4"},{"doi-asserted-by":"crossref","unstructured":"Hermansky, H., Sharma, S.: TRAPS, classifiers of temporal patterns. In: Proc. Int. Conf. Spoken Language Processing. I.\u00a0S.\u00a0C. Association, Syndey (1998)","key":"2_CR5","DOI":"10.21437\/ICSLP.1998-524"},{"unstructured":"Tibrewala, S., Hermansky, H.: Multi-stream approach in acoustic modeling. In: Proc. DARPA Large Vocabulary Continuous Speech Recognition Hub 5 Workshop, pp. 1255\u20131258 (1997)","key":"2_CR6"},{"unstructured":"Tibrewala, S., Hermansky, H.: Sub-band based recognition of noisy speech. In: Proc. Int. Conf. Spoken Language Processing. International Speech Communication Association (1997)","key":"2_CR7"},{"unstructured":"Sharma, S.: Multi-stream approach to robust speech recognition. Ph.D. dissertation, Oregon Graduate Institute of Science and Technology, Portland, Oregon (1999)","key":"2_CR8"},{"doi-asserted-by":"crossref","unstructured":"Jain, P., Hermansky, H.: Beyond a single critical-band in TRAP based ASR. In: Proc. Eurospeech, pp. 437\u2013440 (2003)","key":"2_CR9","DOI":"10.21437\/Eurospeech.2003-164"},{"issue":"5","key":"2_CR10","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.1109\/JPROC.2012.2236871","volume":"101","author":"H. Hermansky","year":"2013","unstructured":"Hermansky, H.: Multistream recognition of speech: Dealing with unknown unknowns (invited paper). Proceedings of Institute of Electriocal and Electronics Engineers\u00a0101(5), 1076\u20131088 (2013)","journal-title":"Proceedings of Institute of Electriocal and Electronics Engineers"},{"key":"2_CR11","volume-title":"Speech and Hearing in Communication","author":"H. Fletcher","year":"1953","unstructured":"Fletcher, H.: Speech and Hearing in Communication. Krieger, New York (1953)"},{"unstructured":"Duchnowski, P.: A new structure for automatic speech recognition. Ph.D. dissertation, Massachusetts Instittute of Technology, Cambridge, MA (1992)","key":"2_CR12"},{"unstructured":"Bourlard, H., Dupont, S., Hermansky, H., Morgan, N.: Towards subband-based speech recognition. In: Proc. EUSIPCO 1996, pp. 1579\u20131582 (1996)","key":"2_CR13"},{"doi-asserted-by":"crossref","unstructured":"Hermansky, H., Tibrewala, S., Pavel, M.: Towards ASR on partially corrupted speech. In: Proc. Int. Conf. Spoken Language Processing, pp. 462\u2013465 (1996)","key":"2_CR14","DOI":"10.21437\/ICSLP.1996-123"},{"doi-asserted-by":"crossref","unstructured":"Bourlard, H., Dupont, S.: A new ASR approach based on independent processing and re-combination of partial frequency bands. In: Proc. Int. Conf. Spoken Language Processing, pp. 426\u2013429 (1996)","key":"2_CR15","DOI":"10.21437\/ICSLP.1996-90"},{"unstructured":"Allen, J.B.: Personal communicaton. DoD Summer Workshop at Rutgers University (1993)","key":"2_CR16"},{"doi-asserted-by":"crossref","unstructured":"Allen, J.B.: Articulation and Intelligibility. Morgan & Claypool (2005)","key":"2_CR17","DOI":"10.2200\/S00004ED1V01Y200508SAP001"},{"doi-asserted-by":"crossref","unstructured":"Hermansky, H.: History of modulation spectrum in ASR. In: Proc. IEEE Int. Conf. Acoust., Speech and Signal Processing, pp. 5458\u20135461 (2010)","key":"2_CR18","DOI":"10.1109\/ICASSP.2010.5494907"},{"issue":"5","key":"2_CR19","first-page":"729","volume":"36","author":"H. Hermansky","year":"2011","unstructured":"Hermansky, H.: Speech recognition from spectral dynamics (invited paper). S\u0101dhan\u0101, Indian Academy of Sciences\u00a036(5), 729\u2013744 (2011)","journal-title":"S\u0101dhan\u0101, Indian Academy of Sciences"},{"key":"2_CR20","doi-asserted-by":"crossref","DOI":"10.4159\/harvard.9780674419193","volume-title":"Relative Frequency of English Speech Sounds","author":"E. Dewey","year":"1923","unstructured":"Dewey, E.: Relative Frequency of English Speech Sounds. Harvard University Press, Cambridge (1923)"},{"issue":"2","key":"2_CR21","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1121\/1.1907526","volume":"27","author":"G.A. Miller","year":"1955","unstructured":"Miller, G.A., Nicely, P.: An analysis of perceptual confusions among some english consonants. J. Acoust. Soc. Amer.\u00a027(2), 338\u2013352 (1955)","journal-title":"J. Acoust. Soc. Amer."},{"issue":"1","key":"2_CR22","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1121\/1.3595744","volume":"139","author":"N. Mesgarani","year":"2011","unstructured":"Mesgarani, N., Thomas, S., Hermansky, H.: Towards optimizing stream fusion. Express Letters of the Acoustical Society of America\u00a0139(1), 14\u201318 (2011)","journal-title":"Express Letters of the Acoustical Society of America"},{"doi-asserted-by":"crossref","unstructured":"Variani, E., Hermansky, H.: Estimating classifier performance in unknown noise. To appear in Proc. Interspeech (2012)","key":"2_CR23","DOI":"10.21437\/Interspeech.2012-490"},{"doi-asserted-by":"crossref","unstructured":"Mesgarani, N., Thomas, S., Hermansky, H.: Adaptive stream fusion in multistream recognition of speech. In: Proc. Interspeech, pp. 2329\u20132332 (2011)","key":"2_CR24","DOI":"10.21437\/Interspeech.2011-618"},{"doi-asserted-by":"crossref","unstructured":"Hermansky, H., Variani, E., Peddinti, V.: Mean temporal distance: Predicting asr error from temporal properties of speech signal. JHU Center for Language and Speech Processing. Technical Report (December 2012)","key":"2_CR25","DOI":"10.1109\/ICASSP.2013.6639105"},{"doi-asserted-by":"crossref","unstructured":"Variani, E., Peng, L., Hermansky, H.: Multi-stream recogntion of noisy speech with performance monitoring. In: Proceedings Interspeech (2013)","key":"2_CR26","DOI":"10.21437\/Interspeech.2013-273"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40585-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T22:53:36Z","timestamp":1688424816000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40585-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642405846","9783642405853"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40585-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}