{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,6]],"date-time":"2022-04-06T02:34:46Z","timestamp":1649212486268},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2010,1,28]],"date-time":"2010-01-28T00:00:00Z","timestamp":1264636800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2011,3]]},"DOI":"10.1007\/s11042-010-0465-7","type":"journal-article","created":{"date-parts":[[2010,1,27]],"date-time":"2010-01-27T11:37:52Z","timestamp":1264592272000},"page":"187-199","source":"Crossref","is-referenced-by-count":3,"title":["Temporal modulation normalization for robust speech feature extraction and recognition"],"prefix":"10.1007","volume":"52","author":[{"given":"Xugang","family":"Lu","sequence":"first","affiliation":[]},{"given":"Shigeki","family":"Matsuda","sequence":"additional","affiliation":[]},{"given":"Masashi","family":"Unoki","sequence":"additional","affiliation":[]},{"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,1,28]]},"reference":[{"key":"465_CR1","doi-asserted-by":"crossref","unstructured":"Atlas L, Shamma S (2003) Joint acoustic and modulation frequency. EURASIP JASP, no 7, pp 668\u2013675","DOI":"10.1155\/S1110865703305013"},{"issue":"1","key":"465_CR2","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/TASL.2006.876717","volume":"15","author":"CP Chen","year":"2007","unstructured":"Chen CP, Bilmes J (2007) MVA processing of speech features. IEEE Trans on Audio, Speech, and Language Processing 15(1):257\u2013270","journal-title":"IEEE Trans on Audio, Speech, and Language Processing"},{"issue":"5","key":"465_CR3","doi-asserted-by":"crossref","first-page":"2670","DOI":"10.1121\/1.409836","volume":"95","author":"R Drullman","year":"1994","unstructured":"Drullman R, Festen JM, Plomp R (1994) Effects of reducing slow temporal modulations on speech reception. J Acoust Soc Am 95(5):2670\u20132680","journal-title":"J Acoust Soc Am"},{"issue":"10","key":"465_CR4","doi-asserted-by":"crossref","first-page":"1141","DOI":"10.1109\/TIP.2002.801126","volume":"11","author":"M Elad","year":"2002","unstructured":"Elad M (2002) On the origin of the bilateral filter and ways to improve it. IEEE Trans Image Process 11(10):1141\u20131151","journal-title":"IEEE Trans Image Process"},{"key":"465_CR5","unstructured":"ETSI ES 202 050 V1.1.5 (2007) Speech processing, transmission and quality aspects (STQ); distributed speech recognition; advanced front-end feature extraction algorithms; compression algorithms. ETSI standard"},{"key":"465_CR6","unstructured":"Fujimoto M, Nakamura S (2006) Sequential non-stationary noise tracking using particle filtering with switching dynamic system. ICASSP06, vol I, pp 769\u2013773"},{"key":"465_CR7","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/ICASSP.1993.319236","volume":"93","author":"H Hermansky","year":"1993","unstructured":"Hermansky H, Morgan N, Hirsch HG (1993) Recognition of speech in additive and convolutional noise based on RASTA spectral processing. ICASSP93, pp 83\u201386","journal-title":"ICASSP"},{"issue":"3","key":"465_CR8","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1121\/1.392224","volume":"77","author":"T Houtgast","year":"1985","unstructured":"Houtgast T, Steeneken HJM (1985) A review of the MTF concept in room acoustics and its use for estimating speech intelligibility in auditoria. J Acoust Soc Am 77(3):1069\u20131077","journal-title":"J Acoust Soc Am"},{"key":"465_CR9","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1109\/TSA.2005.857801","volume":"14","author":"J Hung","year":"2006","unstructured":"Hung J, Lee LS (2006) Optimization of temporal filters for constructing robust features in speech recognition. IEEE Trans on Audio, Speech and Language Processing 14:808\u2013832","journal-title":"IEEE Trans on Audio, Speech and Language Processing"},{"issue":"1","key":"465_CR10","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/S0167-6393(99)00002-3","volume":"28","author":"N Kanedera","year":"1999","unstructured":"Kanedera N, Arai T, Hermansky H, Pavel M (1999) On the relative importance of various components of the modulation spectrum for automatic speech recognition. Speech Commun 28(1):43\u201355","journal-title":"Speech Commun"},{"key":"465_CR11","doi-asserted-by":"crossref","unstructured":"Loizou PC (2007) Speech enhancement: theory and practice. CRC Press","DOI":"10.1201\/9781420015836"},{"key":"465_CR12","first-page":"4573","volume":"09","author":"X Lu","year":"2009","unstructured":"Lu X, Matsuda S, Unoki M, Shimizu T, Nakamura S (2009) Temporal contrast normalization and edge-preserved smoothing on temporal modulation structure for robust speech recognition. ICASSP09, pp 4573\u20134576","journal-title":"ICASSP"},{"key":"465_CR13","unstructured":"Moore BCJ (2003) An introduction to the psychology of hearing. Emerald Group Publishing Ltd"},{"key":"465_CR14","first-page":"1617","volume-title":"Integration of audio-visual sensors and technologies in a smart room","author":"J Neumann","year":"2007","unstructured":"Neumann J, Gasas JR, Macho D, Hidalgo JR (2007) Integration of audio-visual sensors and technologies in a smart room. Personal and Ubiquitous Computing, Springer London, ISSN: pp 1617\u20134909"},{"key":"465_CR15","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1126\/science.270.5234.303","volume":"270","author":"RV Shannon","year":"1995","unstructured":"Shannon RV, Zeng F, Kamath V, Wygonski J, Ekelid M (1995) Speech recognition with primarily temporal cues. Science 270:303\u2013304","journal-title":"Science"},{"key":"465_CR16","first-page":"881","volume":"96","author":"JL Shen","year":"1996","unstructured":"Shen JL, Hwang WL, Lee LS (1996) Robust speech recognition features based on temporal trajectory filtering of frequency band spectrum. ICSLP96, pp 881\u2013884","journal-title":"ICSLP"},{"key":"465_CR17","volume-title":"The HTK Book (version 3.2)","author":"Young","year":"2002","unstructured":"Young et al. (2002) The HTK Book (version 3.2) Cambridge University Engineering Department, UK"},{"issue":"3","key":"465_CR18","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1109\/TSA.2005.845805","volume":"13","author":"A Torre","year":"2005","unstructured":"Torre A, Peinado AM, Segura JC, Crdoba JLP, Bentez MC, Rubio AJ (2005) Histogram equalization of speech representation for robust speech recognition. IEEE Trans Speech Audio Process 13(3):355\u2013366","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"7","key":"465_CR19","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/LSP.2006.891341","volume":"14","author":"X Xiao","year":"2007","unstructured":"Xiao X, Chng ES, Li H (2007) Temporal structure normalization of speech feature for robust speech recognition. IEEE Signal Process Lett 14(7):500\u2013503","journal-title":"IEEE Signal Process Lett"},{"issue":"8","key":"465_CR20","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.1109\/TASL.2008.2002082","volume":"16","author":"X Xiao","year":"2008","unstructured":"Xiao X, Chng ES, Li H (2008) Normalization of speech modulation spectra for robust speech recognition. IEEE Trans on Audio, Speech, and Language Processing 16(8):1662\u20131674","journal-title":"IEEE Trans on Audio, Speech, and Language Processing"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-010-0465-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-010-0465-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-010-0465-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T03:27:54Z","timestamp":1559359674000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-010-0465-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,1,28]]},"references-count":20,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2011,3]]}},"alternative-id":["465"],"URL":"https:\/\/doi.org\/10.1007\/s11042-010-0465-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,1,28]]}}}