{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T20:32:31Z","timestamp":1762374751517,"version":"3.30.2"},"reference-count":36,"publisher":"Elsevier BV","issue":"2-3","license":[{"start":{"date-parts":[[2003,10,1]],"date-time":"2003-10-01T00:00:00Z","timestamp":1064966400000},"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":["Speech Communication"],"published-print":{"date-parts":[[2003,10]]},"DOI":"10.1016\/s0167-6393(03)00016-5","type":"journal-article","created":{"date-parts":[[2003,5,1]],"date-time":"2003-05-01T00:39:38Z","timestamp":1051749578000},"page":"469-484","source":"Crossref","is-referenced-by-count":34,"title":["Cepstrum derived from differentiated power spectrum for robust speech recognition"],"prefix":"10.1016","volume":"41","author":[{"given":"Jingdong","family":"Chen","sequence":"first","affiliation":[]},{"given":"Kuldip K.","family":"Paliwal","sequence":"additional","affiliation":[]},{"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(03)00016-5_BIB1","doi-asserted-by":"crossref","unstructured":"Andrassy, B., Vlaj, D., Beaugeant, C., 2001. Recognition performance of the Siemens front-end with and without frame dropping on the AURORA 2 database. Proc. EUROSPEECH, Scandinavia, pp. 193\u2013196","DOI":"10.21437\/Eurospeech.2001-71"},{"issue":"2","key":"10.1016\/S0167-6393(03)00016-5_BIB2","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 Trans. Acoustics, Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB3","doi-asserted-by":"crossref","unstructured":"Bourlard, H., Dupont, S., 1996. A new ASR approach based on independent processing and recombination of partial frequency bands. Proc. ICSLP, Philadelphia, pp. 426\u2013429","DOI":"10.21437\/ICSLP.1996-90"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB4","doi-asserted-by":"crossref","unstructured":"Chen, J., Paliwal, K.K., Nakamura, S., 2001. Sub-band based additive noise removal for robust speech recognition. Proc. EUROSPEECH, Scandinavia, pp. 571\u2013574","DOI":"10.21437\/Eurospeech.2001-152"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB5","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","article-title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","volume":"28","author":"Davis","year":"1980","journal-title":"IEEE Trans. Acoustics, Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB6","doi-asserted-by":"crossref","unstructured":"Droppo, J., Deng, L., Acero, A., 2001. Evaluation of the SPLICE algorithm on the Aurora2 database. Proc. EUROSPEECH, Scandinavia, pp. 217\u2013220","DOI":"10.21437\/Eurospeech.2001-77"},{"issue":"1","key":"10.1016\/S0167-6393(03)00016-5_BIB7","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/TASSP.1986.1164788","article-title":"Speaker-independent isolated work recognition using dynamic features of speech spectrum","volume":"34","author":"Furui","year":"1986","journal-title":"IEEE Trans. Acoustics, Speech Signal Process."},{"issue":"5","key":"10.1016\/S0167-6393(03)00016-5_BIB8","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1109\/89.536929","article-title":"Robust speech recognition using parallel model combination","volume":"4","author":"Gales","year":"1996","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB9","unstructured":"Geller, D., Haeb-Umbach, R., Ney, H., 1992. Improvements in speech recognition for voice dialing in the car environment. Proc. ESCA Workshop on Speech Processing in Adverse Conditions, Mandelieu, pp. 203\u2013206"},{"issue":"4","key":"10.1016\/S0167-6393(03)00016-5_BIB10","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":"J. Acoustic. Soc. Am."},{"issue":"4","key":"10.1016\/S0167-6393(03)00016-5_BIB11","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/89.326616","article-title":"RASTRA of processing of speech","volume":"2","author":"Hermansky","year":"1994","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB12","doi-asserted-by":"crossref","unstructured":"Hermansky, H., Morgan, N., Bayya, A., Kohn, P. 1991. Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP). Proc. EUROSPEECH, Genova, pp. 1367\u20131370","DOI":"10.21437\/Eurospeech.1991-312"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB13","doi-asserted-by":"crossref","unstructured":"Hirsch, H., Meyer, P., Ruehl, H., 1991. Improved speech recognition using high-pass filtering of subband envelopes. Proc. EUROSPEECH, Genova, pp. 413\u2013416","DOI":"10.21437\/Eurospeech.1991-105"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB14","unstructured":"Hirsch, H.G., 2000. The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions. Proc. ISCA ASR2000, Paris, France"},{"issue":"7","key":"10.1016\/S0167-6393(03)00016-5_BIB15","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1109\/TASSP.1987.1165237","article-title":"On the use of bandpass liftering in speech recognition","volume":"35","author":"Juang","year":"1987","journal-title":"IEEE Trans. Acoust., Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB16","unstructured":"Junqua, J.-C., Cerisara, C., Rigazio, L., Kryze, D., 2001. Environment-adaptive algorithms for robust speech recognition. Proc. Internat. Workshop Handsfree Speech Communication, Kyoto, Japan, pp. 31\u201334"},{"issue":"1","key":"10.1016\/S0167-6393(03)00016-5_BIB17","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/89.736331","article-title":"Auditory processing of speech signals for robustness speech recognition in real-world noisy environments","volume":"7","author":"Kim","year":"1999","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB18","doi-asserted-by":"crossref","unstructured":"Kotnik, B., Kacic, Z., Horvat, B., 2001. A multiconditional robust front-end feature extraction with a noise reduction procedure based on improved spectral subtraction algorithm. Proc. EUROSPEECH, Scandinavia, pp. 197\u2013200","DOI":"10.21437\/Eurospeech.2001-72"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB19","unstructured":"Lamel, L.F., Kassel, H.K., Seneft, S., 1986. Speech database development: Design and analysis of the acoustic\u2013phonetic corpus. Proc. DARPA Speech Recognition Workshop, Palo Alto, pp. 100\u2013109"},{"issue":"11","key":"10.1016\/S0167-6393(03)00016-5_BIB20","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","article-title":"Speaker-independent phone recognition using hidden Markov models","volume":"37","author":"Lee","year":"1989","journal-title":"IEEE Trans. Acoustics, Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB21","doi-asserted-by":"crossref","unstructured":"Moreno, P.J., Raj, B., Stern, R.M., 1996. A vector Taylor series approach for environment independent speech recognition. Proc. ICSLP, Philadelphia, PA, pp. 733\u2013736","DOI":"10.1109\/ICASSP.1996.543225"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB22","doi-asserted-by":"crossref","unstructured":"Nolazco Flores, J.A., Young, S.J., 1994. Continuous speech recognition in noise using spectral subtraction and HMM adaptation. Proc. ICASSP, Adelaide, Australia, pp. 409\u2013412","DOI":"10.1109\/ICASSP.1994.389269"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB23","doi-asserted-by":"crossref","unstructured":"Ohkura, K., Sugiyama, M., Sagayama, S., 1992. Speaker adaptation based on transfer vector field smoothing technique. Proc. ICSLP, Banff, Canada, pp. 369\u2013372","DOI":"10.21437\/ICSLP.1992-106"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB24","first-page":"151","article-title":"On the performance of the frequency-weighted cepstral coefficients in vowel recognition","volume":"18","author":"Paliwal","year":"1992","journal-title":"Speech Commun."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB25","doi-asserted-by":"crossref","unstructured":"Paliwal, K.K., 1999. Decorrelated and liftered filter-bank energies for robust speech recognition. Proc. EUROPSEECH, Budapest, pp. 85\u201388","DOI":"10.21437\/Eurospeech.1999-25"},{"issue":"9","key":"10.1016\/S0167-6393(03)00016-5_BIB26","doi-asserted-by":"crossref","first-page":"1215","DOI":"10.1109\/5.237532","article-title":"Signal modeling techniques in speech recognition","volume":"81","author":"Picone","year":"1993","journal-title":"Proc. IEEE"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB27","doi-asserted-by":"crossref","unstructured":"Popescu, D.C., Zeljkovic, I., 1998. Kalman filtering of colored noise for speech enhancement. Proc. ICASSP, Seattle, pp. 997\u20131000","DOI":"10.1109\/ICASSP.1998.675435"},{"issue":"1","key":"10.1016\/S0167-6393(03)00016-5_BIB28","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/TSA.1996.481449","article-title":"Signal bias removal by maximum likelihood estimation for robust telephone speech recognition","volume":"4","author":"Rahim","year":"1996","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB29","doi-asserted-by":"crossref","unstructured":"Sagayama, S., Yamaguchi, Y., Tahahashi, S., Takahashi, J.-I., 1997. Jacobian approach to fast acoustic model adaptation, Proc. ICASSP, Munich, Germany, pp. 835\u2013838","DOI":"10.1109\/ICASSP.1997.596063"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB30","doi-asserted-by":"crossref","unstructured":"Soong, F.K., Rosenberg, A.E., 1986. On the use of instantaneous and transitional spectral information in speaker recognition. Proc. ICASSP, Tokyo, Japan, pp. 877\u2013880","DOI":"10.1109\/ICASSP.1986.1168882"},{"issue":"10","key":"10.1016\/S0167-6393(03)00016-5_BIB31","doi-asserted-by":"crossref","first-page":"1414","DOI":"10.1109\/TASSP.1987.1165058","article-title":"A weighted cepstral distance measure for speech recognition","volume":"35","author":"Tohkura","year":"1987","journal-title":"IEEE Trans. Acoust., Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB32","unstructured":"Varga, A., Steeneken, H.J.M., Tomlinson, M., Jones D., 1992. The NOISEX-92 study on the effect of additive noise on automatic speech recognition. DRA Speech Research Unit, St. Andrew\u2019s Rd., Malvern, Worcestershire, WR14 3PS UK"},{"issue":"1","key":"10.1016\/S0167-6393(03)00016-5_BIB33","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/89.554264","article-title":"Noise compensation methods for hidden Markov model speech recognition in adverse environments","volume":"5","author":"Vaseghi","year":"1997","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(03)00016-5_BIB34","doi-asserted-by":"crossref","unstructured":"Woodland, P.C., Gales, M.J.E., Pye, D., 1996. Improving environmental robustness in large vocabulary speech recognition. Proc. ICASSP, Atlanta, GA, pp. 65\u201368","DOI":"10.1109\/ICASSP.1996.540291"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB35","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Iseli, M., Cui, X., Alwan, A., 2001. Noise robust feature extraction for ASR using Aurora 2 database. Proc. EUROSPEECH, Scandinavia, pp. 185\u2013188","DOI":"10.21437\/Eurospeech.2001-69"},{"key":"10.1016\/S0167-6393(03)00016-5_BIB36","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/0167-6393(90)90010-7","article-title":"Speech database development at MIT: TIMIT and beyond","volume":"9","author":"Zue","year":"1990","journal-title":"Speech Commun."}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639303000165?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639303000165?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T01:17:31Z","timestamp":1733966251000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639303000165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,10]]},"references-count":36,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2003,10]]}},"alternative-id":["S0167639303000165"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(03)00016-5","relation":{},"ISSN":["0167-6393"],"issn-type":[{"type":"print","value":"0167-6393"}],"subject":[],"published":{"date-parts":[[2003,10]]}}}