{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T03:15:42Z","timestamp":1769915742273,"version":"3.49.0"},"reference-count":32,"publisher":"Elsevier BV","issue":"1-3","license":[{"start":{"date-parts":[[1998,8,1]],"date-time":"1998-08-01T00:00:00Z","timestamp":901929600000},"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":[[1998,8]]},"DOI":"10.1016\/s0167-6393(98)00032-6","type":"journal-article","created":{"date-parts":[[2003,4,5]],"date-time":"2003-04-05T03:57:58Z","timestamp":1049515078000},"page":"117-132","source":"Crossref","is-referenced-by-count":171,"title":["Robust speech recognition using the modulation spectrogram"],"prefix":"10.1016","volume":"25","author":[{"given":"Brian E.D","family":"Kingsbury","sequence":"first","affiliation":[]},{"given":"Nelson","family":"Morgan","sequence":"additional","affiliation":[]},{"given":"Steven","family":"Greenberg","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(98)00032-6_BIB1","doi-asserted-by":"crossref","unstructured":"Arai, T., Greenberg, S., 1998. Speech intelligibility in the presence of cross-channel spectral asynchrony. Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing","DOI":"10.1109\/ICASSP.1998.675419"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB2","doi-asserted-by":"crossref","unstructured":"Bourlard, H., Morgan, N., 1994. Connectionist Speech Recognition: A Hybrid Approach. Kluwer Academic Publishers, Dordrecht, pp. 155\u2013183","DOI":"10.1007\/978-1-4615-3210-1_7"},{"issue":"2","key":"10.1016\/S0167-6393(98)00032-6_BIB3","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1121\/1.408467","article-title":"Effect of temporal envelope smearing on speech reception","volume":"95","author":"Drullman","year":"1994","journal-title":"J. Acoust. Soc. Amer."},{"issue":"2","key":"10.1016\/S0167-6393(98)00032-6_BIB4","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1121\/1.1916020","article-title":"Remaking speech","volume":"11","author":"Dudley","year":"1939","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00032-6_BIB5","doi-asserted-by":"crossref","unstructured":"Furui, S., 1986. Speaker-independent isolated word recognition based on emphasized spectral dynamics. Proceedings of the 1986 IEEE-IECEJ-ASJ International Conference on Acoustics, Speech and Signal Processing, pp. 1991\u20131994","DOI":"10.1109\/ICASSP.1986.1168654"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB6","unstructured":"Greenberg, S., 1997. On the origins of speech intelligibility in the real world. Proceedings of the ESCA\u2013NATO Workshop on Robust Speech Recognition for Unknown Communication Channels, pp. 23\u201332"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB7","doi-asserted-by":"crossref","unstructured":"Greenberg, S., Arai. T., 1998. Speech intelligibility is highly tolerant of cross-channel spectral asynchrony. Proceedings of the Joint Meeting of the Acoustical Society of America and the International Congress on Acoustics","DOI":"10.1121\/1.422679"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB8","unstructured":"Greenberg, S., Hollenback, J., Ellis, D., 1996. Insights into spoken language gleaned from phonetic transcription of the Switchboard corpus. Proceedings of the Fourth International Conference on Spoken Language Processing, pp. S24\u201327"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB9","doi-asserted-by":"crossref","unstructured":"Greenberg, S., Kingsbury, B.E.D., 1997. The modulation spectrogram: In pursuit of an invariant representation of speech. Proceedings of the 1997 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1647\u20131650","DOI":"10.1109\/ICASSP.1997.598826"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB10","doi-asserted-by":"crossref","first-page":"1344","DOI":"10.1121\/1.1908437","article-title":"Critical bandwidth and the frequency coordinates of the basilar membrane","volume":"33","author":"Greenwood","year":"1961","journal-title":"J. Acoust. Soc. Amer."},{"issue":"4","key":"10.1016\/S0167-6393(98)00032-6_BIB11","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. Acoust. Soc. Amer."},{"issue":"4","key":"10.1016\/S0167-6393(98)00032-6_BIB12","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/89.326616","article-title":"RASTA processing of speech","volume":"2","author":"Hermansky","year":"1994","journal-title":"IEEE Trans. on Speech and Audio Processing"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB13","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/0167-6393(85)90045-7","article-title":"Low-dimensional representation of vowels based on all-pole modeling in the psychophysical domain","volume":"4","author":"Hermansky","year":"1985","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB14","unstructured":"Hirsch, H.G., 1988. Automatic speech recognition in rooms. In: Lacoume, J.L., Chehikian, A., Martin, N., Malbos, J. (Eds.), Signal Processing IV: Theories and Applications, Proceedings of the EUSIPCO-88, Fourth European Signal Processing Conference, Elsevier, Amsterdam, pp. 1177\u20131180"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB15","first-page":"66","article-title":"The modulation transfer function in room acoustics as a predictor of speech intelligibility","volume":"28","author":"Houtgast","year":"1973","journal-title":"Acustica"},{"issue":"3","key":"10.1016\/S0167-6393(98)00032-6_BIB16","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1121\/1.392224","article-title":"A review of the MTF concept in room acoustics and its use for estimating speech intelligibility","volume":"77","author":"Houtgast","year":"1985","journal-title":"J. Acoust. Soc. Amer."},{"issue":"1","key":"10.1016\/S0167-6393(98)00032-6_BIB17","first-page":"60","article-title":"Predicting speech intelligibility in rooms from the modulation transfer function I. General room acoustics","volume":"46","author":"Houtgast","year":"1980","journal-title":"Acustica"},{"issue":"2","key":"10.1016\/S0167-6393(98)00032-6_BIB18","doi-asserted-by":"crossref","first-page":"49","DOI":"10.3758\/BF03204103","article-title":"Temporally segmented speech","volume":"18","author":"Huggins","year":"1975","journal-title":"Perception and Psychophysics"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB19","doi-asserted-by":"crossref","unstructured":"Kingsbury, B.E.D., Morgan, N., 1997. Recognizing reverberant speech with RASTA-PLP. Proceedings of the 1997 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1259\u20131262","DOI":"10.1109\/ICASSP.1997.596174"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB20","unstructured":"Kingsbury, B.E.D., Morgan, N., Greenberg, S., 1997. Improving ASR performance for reverberant speech. Proceedings of the ESCA\u2013NATO Workshop on Robust Speech Recognition for Unknown Communication Channels, pp. 87\u201390"},{"issue":"3","key":"10.1016\/S0167-6393(98)00032-6_BIB21","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1121\/1.408546","article-title":"Speech enhancement based on physiological and psychoacoustical models of modulation perception and binaural interaction","volume":"95","author":"Kollmeier","year":"1994","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00032-6_BIB22","doi-asserted-by":"crossref","unstructured":"Langhans, T., Strube, H.W., 1982. Speech enhancement by nonlinear multiband envelope filtering. Proceedings of the 1982 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 156\u2013159","DOI":"10.1109\/ICASSP.1982.1171715"},{"issue":"4","key":"10.1016\/S0167-6393(98)00032-6_BIB23","doi-asserted-by":"crossref","first-page":"379","DOI":"10.3758\/BF03206730","article-title":"Minimal spectral contrast of formant peaks for vowel recognition as a function of spectral slope","volume":"56","author":"Lea","year":"1994","journal-title":"Perception and Psychophysics"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB24","doi-asserted-by":"crossref","unstructured":"Leonard, R.G., 1984. A database for speaker-independent digit recognition. Proceedings of the 1984 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 42.11.1\u201342.11-4","DOI":"10.1109\/ICASSP.1984.1172716"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB25","doi-asserted-by":"crossref","unstructured":"Milner, B.P., Vaseghi, S.V., 1995. An analysis of cepstral-time matrices for noise and channel robust speech recognition. EUROSPEECH 95, Proceedings of the Fourth European Conference on Speech Communication and Technology, pp. 519\u2013522","DOI":"10.21437\/Eurospeech.1995-138"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB26","doi-asserted-by":"crossref","unstructured":"Morgan, N., Hermansky, H., 1992. RASTA extensions: Robustness to additive and convolutional noise. ESCA Workshop on Speech Processing in Adverse Conditions, pp. 115\u2013118","DOI":"10.1109\/ICASSP.1993.319236"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB27","doi-asserted-by":"crossref","unstructured":"Ramsay, G., Deng, L., 1995. Maximum-likelihood estimation for articulatory speech recognition using a stochastic target model. EUROSPEECH 95, Proceedings of the Fourth European Conference on Speech Communication and Technology, pp. 1401\u20131404","DOI":"10.21437\/Eurospeech.1995-225"},{"issue":"1","key":"10.1016\/S0167-6393(98)00032-6_BIB28","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/0378-5955(88)90146-3","article-title":"Representation of amplitude modulation in the auditory cortex of the cat. II. Comparison between cortical fields","volume":"32","author":"Schreiner","year":"1988","journal-title":"Hearing Research"},{"issue":"1","key":"10.1016\/S0167-6393(98)00032-6_BIB29","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1121\/1.384464","article-title":"A physical method for measuring speech-transmission quality","volume":"67","author":"Steeneken","year":"1980","journal-title":"J. Acoust. Soc. Amer."},{"issue":"3","key":"10.1016\/S0167-6393(98)00032-6_BIB30","doi-asserted-by":"crossref","first-page":"203","DOI":"10.3758\/BF03205933","article-title":"Perceiving vowels from uniform spectra: Phonetic exploration of an auditory aftereffect","volume":"35","author":"Summerfield","year":"1984","journal-title":"Perception and Psychophysics"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB31","unstructured":"Wu, S.-L., 1998. Incorporating information from syllable-length time scales into automatic speech recognition. Ph. D Thesis, University of California, Berkeley"},{"key":"10.1016\/S0167-6393(98)00032-6_BIB32","unstructured":"Wu, S.-L., Kingsbury, B.E.D., Morgan, N., Greenberg, S., 1998. Incorporating information from syllable-length time scales into automatic speech recognition. Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639398000326?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639398000326?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T21:59:40Z","timestamp":1681595980000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639398000326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,8]]},"references-count":32,"journal-issue":{"issue":"1-3","published-print":{"date-parts":[[1998,8]]}},"alternative-id":["S0167639398000326"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(98)00032-6","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[1998,8]]}}}