{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T09:46:39Z","timestamp":1720172799235},"reference-count":30,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2013,9,1]],"date-time":"2013-09-01T00:00:00Z","timestamp":1377993600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2013,9]]},"DOI":"10.1016\/j.neunet.2013.02.006","type":"journal-article","created":{"date-parts":[[2013,3,8]],"date-time":"2013-03-08T11:51:08Z","timestamp":1362743468000},"page":"62-69","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Nonlinear spectro-temporal features based on a cochlear model for automatic speech recognition in a noisy situation"],"prefix":"10.1016","volume":"45","author":[{"given":"Yong-Sun","family":"Choi","sequence":"first","affiliation":[]},{"given":"Soo-Young","family":"Lee","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.neunet.2013.02.006_br000005","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","article-title":"Suppression of acoustic noise in speech using spectral subtraction","volume":"27","author":"Boll","year":"1979","journal-title":"IEEE Transactions on Acoustics, Speech, & Signal Processing"},{"issue":"9","key":"10.1016\/j.neunet.2013.02.006_br000010","doi-asserted-by":"crossref","first-page":"1943","DOI":"10.1109\/78.134427","article-title":"Speech enhancement based conceptually on auditory evidence","volume":"39","author":"Cheng","year":"1991","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.1016\/j.neunet.2013.02.006_br000015","series-title":"Advances in neural information processing systems","article-title":"Phone recognition with the mean\u2013covariance","author":"Dahl","year":"2010"},{"key":"10.1016\/j.neunet.2013.02.006_br000020","doi-asserted-by":"crossref","DOI":"10.1109\/TASL.2011.2134090","article-title":"Context-dependent pre-trained deep neural networks for large vocabulary speech recognition","author":"Dahl","year":"2012","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"10.1016\/j.neunet.2013.02.006_br000025","series-title":"The cochlea","volume":"vol. 8","author":"Dallos","year":"1996"},{"key":"10.1016\/j.neunet.2013.02.006_br000030","unstructured":"ETSI (2000). Speech processing, transmission and quality aspects (STQ); Distributed speech recognition; Front-end feature extraction algorithm; Compression algorithms. ETSI ES 201 108 V1.1.2. In http:\/\/www.etsi.org."},{"key":"10.1016\/j.neunet.2013.02.006_br000035","doi-asserted-by":"crossref","first-page":"2592","DOI":"10.1121\/1.399052","article-title":"A cochlear frequency-position function for several species-29 years later","volume":"87","author":"Greenwood","year":"1990","journal-title":"Journal of the Acoustical Society of America"},{"key":"10.1016\/j.neunet.2013.02.006_br000040","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.specom.2008.06.002","article-title":"Perceptual features for automatic speech recognition in noisy environments","volume":"51","author":"Haque","year":"2009","journal-title":"Speech Communication"},{"issue":"4","key":"10.1016\/j.neunet.2013.02.006_br000045","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","article-title":"Perceptual linear predictive (PLP) analysis of speech","volume":"87","author":"Hermansky","year":"1990","journal-title":"Journal of the Acoustical Society of America"},{"issue":"4","key":"10.1016\/j.neunet.2013.02.006_br000050","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"Hermansky","year":"1994","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"10.1016\/j.neunet.2013.02.006_br000055","unstructured":"Hirsch, H. G., & Pearce, D. (2000). The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In Proc. ISCA ITRW ASR2000 (pp. 181\u2013188)."},{"issue":"1","key":"10.1016\/j.neunet.2013.02.006_br000060","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TSA.2005.860349","article-title":"Automatic speech recognition with an adaptation model motivated by auditory processing","volume":"14","author":"Holmberg","year":"2006","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"10.1016\/j.neunet.2013.02.006_br000065","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/89.736331","article-title":"Auditory processing of speech signals for robust speech recognition in real-world noisy environments","volume":"7","author":"Kim","year":"1999","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"10.1016\/j.neunet.2013.02.006_br000070","doi-asserted-by":"crossref","unstructured":"Lee, J., & Lee, S. -Y. (2011). Deep learning of speech features for improved phonetic recognition. In INTERSPEECH-2011 (pp. 1249\u20131252).","DOI":"10.21437\/Interspeech.2011-98"},{"issue":"1\u20133","key":"10.1016\/j.neunet.2013.02.006_br000075","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1016\/j.neucom.2008.07.005","article-title":"Binaural semi-blind dereverberation of noisy convoluted speech signals","volume":"72","author":"Lee","year":"2008","journal-title":"Neurocomputing"},{"issue":"4","key":"10.1016\/j.neunet.2013.02.006_br000080","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/S0166-2236(97)01192-2","article-title":"How well do we understand the cochlea?","volume":"21","author":"Nobili","year":"1998","journal-title":"Trends in Neurosciences"},{"key":"10.1016\/j.neunet.2013.02.006_br000085","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1016\/S0925-2312(02)00791-9","article-title":"An engineering model of the masking for the noise-robust speech recognition","volume":"52\u201354","author":"Park","year":"2003","journal-title":"Neurocomputing"},{"issue":"1\u20133","key":"10.1016\/j.neunet.2013.02.006_br000090","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.neucom.2009.08.009","article-title":"A bark-scale filter bank approach to independent component analysis for acoustic mixtures","volume":"73","author":"Park","year":"2009","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.neunet.2013.02.006_br000095","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1121\/1.428318","article-title":"Basilar-membrane nonlinearity estimated by pulsation threshold","volume":"107","author":"Plack","year":"2000","journal-title":"Journal of the Acoustical Society of America"},{"key":"10.1016\/j.neunet.2013.02.006_br000100","doi-asserted-by":"crossref","first-page":"2773","DOI":"10.1121\/1.1564018","article-title":"Measurements of human middle ear forward and reverse acoustics: implications for otoacoustic emissions","volume":"113","author":"Puria","year":"2003","journal-title":"Journal of the Acoustical Society of America"},{"issue":"2","key":"10.1016\/j.neunet.2013.02.006_br000105","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden Markov models and selected applications in speech recognition","volume":"77","author":"Rabiner","year":"1989","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.neunet.2013.02.006_br000110","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2007\/65420","article-title":"An FFT-based companding front end for noise-robust automatic speech recognition","author":"Raj","year":"2007","journal-title":"EURASIP Journal on Audio, Speech and Music Processing"},{"issue":"6","key":"10.1016\/j.neunet.2013.02.006_br000115","doi-asserted-by":"crossref","first-page":"3140","DOI":"10.1121\/1.1416198","article-title":"Multicomponent stimulus interactions observed in basilar-membrane vibration in the basal region of the chinchilla cochlea","volume":"110","author":"Rhode","year":"2001","journal-title":"Journal of the Acoustical Society of America"},{"key":"10.1016\/j.neunet.2013.02.006_br000120","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/S0095-4470(19)30466-8","article-title":"A joint synchrony\/mean rate model of auditory speech processing","volume":"16","author":"Seneff","year":"1988","journal-title":"Journal of Phonetics"},{"key":"10.1016\/j.neunet.2013.02.006_br000125","series-title":"Electrocochleography","first-page":"183","article-title":"Comparison of human and animal data concerning adaptation and masking of eighth nerve compound action potential","author":"Spoor","year":"1976"},{"key":"10.1016\/j.neunet.2013.02.006_br000130","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1121\/1.1915893","article-title":"A scale for the measurement of the psychological magnitude pitch","volume":"8","author":"Stevens","year":"1937","journal-title":"Journal of the Acoustical Society of America"},{"issue":"5","key":"10.1016\/j.neunet.2013.02.006_br000135","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1109\/89.622569","article-title":"A model of dynamic auditory perception and its application to robust word recognition","volume":"5","author":"Strope","year":"1997","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"7","key":"10.1016\/j.neunet.2013.02.006_br000140","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1109\/LSP.2006.891313","article-title":"Convolutional bias removal based on normalizing the filterbank spectral magnitude","volume":"14","author":"Tufekci","year":"2007","journal-title":"IEEE Signal Processing Letters"},{"issue":"2","key":"10.1016\/j.neunet.2013.02.006_br000145","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1109\/89.748118","article-title":"Single channel speech enhancement based on masking properties of the human auditory system","volume":"7","author":"Virag","year":"1999","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"10.1016\/j.neunet.2013.02.006_br000150","series-title":"Psychoacoustics: facts and models","author":"Zwicker","year":"1990"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608013000476?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608013000476?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2022,7,2]],"date-time":"2022-07-02T20:12:46Z","timestamp":1656792766000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608013000476"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9]]},"references-count":30,"alternative-id":["S0893608013000476"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2013.02.006","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2013,9]]}}}