{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T11:56:27Z","timestamp":1775303787430,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030057152","type":"print"},{"value":"9783030057169","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,12,11]],"date-time":"2018-12-11T00:00:00Z","timestamp":1544486400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-05716-9_12","type":"book-chapter","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T14:17:32Z","timestamp":1544451452000},"page":"144-156","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Spectral Tilt Estimation for Speech Intelligibility Enhancement Using RNN Based on All-Pole Model"],"prefix":"10.1007","author":[{"given":"Rui","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Ruimin","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiaochen","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,11]]},"reference":[{"issue":"2","key":"12_CR1","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/MSP.2014.2365594","volume":"32","author":"WB Kleijn","year":"2015","unstructured":"Kleijn, W.B., Crespo, J.B., Hendriks, R.C., et al.: Optimizing speech intelligibility in a noisy environment: a unified view. IEEE Signal Process. Mag. 32(2), 43\u201354 (2015)","journal-title":"IEEE Signal Process. Mag."},{"key":"12_CR2","unstructured":"Sauert, B., Vary, P.: Near end listening enhancement optimized with respect to speech intelligibility index. In: 17th European Signal Processing Conference, pp. 1844\u20131848. IEEE (2009)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Schepker, H., Rennies, J., Doclo, S.: Improving speech intelligibility in noise by SII-dependent preprocessing using frequency-dependent amplification and dynamic range compression. In: Proceedings of Interspeech, pp. 3577\u20133581. ISCA, Lyon (2013)","DOI":"10.21437\/Interspeech.2013-769"},{"issue":"2","key":"12_CR4","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1109\/TASLP.2014.2384271","volume":"23","author":"PN Petkov","year":"2015","unstructured":"Petkov, P.N., Kleijn, W.B.: Spectral dynamics recovery for enhanced speech intelligibility in noise. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(2), 327\u2013338 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Petko, P.N., Stylinaou, Y.: Adaptive gain control and time warp for enhanced speech intelligibility under reverberation. In: IEEE International Conference on Acoustic, Speech and Signal Processing (IASSP), New Orleans, pp. 691\u2013695. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952244"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Zoril\u00e2, T.C., Kandia, V., Stylianou, Y.: Speech-in-noise intelligibility improvement based on spectral shaping and dynamic range compression. In: Proceedings Interspeech, pp. 635\u2013638. ISCA, Portland (2012)","DOI":"10.21437\/Interspeech.2012-197"},{"issue":"10","key":"12_CR7","doi-asserted-by":"publisher","first-page":"1808","DOI":"10.1109\/TASLP.2016.2585864","volume":"24","author":"TC Zoril\u00e2","year":"2016","unstructured":"Zoril\u00e2, T.C., Stylianou, Y., Ishihara, T., et al.: Near and far field speech-in-noise intelligibility improvements based on a time-frequency energy reallocation approach. IEEE Trans. Audio Speech Lang. Process. 24(10), 1808\u20131818 (2016)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Jokinen, E., Remes, U., Takanen, M., et al: Spectral tilt modelling with GMMs for intelligibility enhancement of narrowband telephone speech. In: Proceedings of Interspeech, pp. 2036\u20132040. ISCA, Singapore (2014)","DOI":"10.1109\/IWAENC.2014.6953999"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Jokinen, E., Remes, U., Alku, P.: The use of read versus conversational Lombard speech in spectral tilt modeling for intelligibility enhancement in near-end noise conditions. In: Proceedings of Interspeech, pp. 2771\u20132775. ISCA, San Francisco (2016)","DOI":"10.21437\/Interspeech.2016-143"},{"issue":"10","key":"12_CR10","doi-asserted-by":"publisher","first-page":"1985","DOI":"10.1109\/TASLP.2017.2740004","volume":"25","author":"E Jokinen","year":"2017","unstructured":"Jokinen, E., Remes, U., Alku, P.: Intelligibility enhancement of telephone speech using gaussian process regression for normal-to-lombard spectral tilt conversion. IEEE Trans. Audio Speech Lang. Process. 25(10), 1985\u20131996 (2017)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"84","key":"12_CR11","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1121\/1.396660","volume":"3","author":"WV Summers","year":"1988","unstructured":"Summers, W.V., Pisoni, D.B., Bernacki, R.H., et al.: Effects of noise on speech production: acoustic and perceptual analyses. J. Acoust. Soc. Am. 3(84), 917\u2013928 (1988)","journal-title":"J. Acoust. Soc. Am."},{"issue":"1","key":"12_CR12","first-page":"117","volume":"86","author":"AW Bronkhorst","year":"2000","unstructured":"Bronkhorst, A.W.: The cocktail party phenomenon: a review of research on speech intelligibility in multiple-talker conditions. Acta Acust. United Acust. 86(1), 117\u2013128 (2000)","journal-title":"Acta Acust. United Acust."},{"issue":"12","key":"12_CR13","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1016\/j.specom.2009.07.002","volume":"51","author":"Y Lu","year":"2009","unstructured":"Lu, Y., Cooke, M.: The contribution of change in F0 and spectral tilt to increased intelligibility of speech produced in noise. Speech Commun. 51(12), 1253\u20131262 (2009)","journal-title":"Speech Commun."},{"issue":"4","key":"12_CR14","doi-asserted-by":"publisher","first-page":"2059","DOI":"10.1121\/1.3478775","volume":"128","author":"M Cooke","year":"2010","unstructured":"Cooke, M., Lu, Y.: Spectral and temporal changes to speech produced in the presence of energetic and informational masker. J. Acoust. Soc. Am. 128(4), 2059\u20132069 (2010)","journal-title":"J. Acoust. Soc. Am."},{"issue":"4","key":"12_CR15","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1121\/1.4979162","volume":"141","author":"E Jokinen","year":"2017","unstructured":"Jokinen, E., Alku, P.: Estimating the spectral tilt of the glottal source from telephone speech using neural network. J. Acoust. Soc. Am. Express Lett. 141(4), 327\u2013330 (2017)","journal-title":"J. Acoust. Soc. Am. Express Lett."},{"issue":"4","key":"12_CR16","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1109\/PROC.1975.9792","volume":"63","author":"J Makhoul","year":"1975","unstructured":"Makhoul, J.: Linear prediction: a tutorial review. Proc. IEEE 63(4), 561\u2013580 (1975)","journal-title":"Proc. IEEE"},{"issue":"2","key":"12_CR17","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1109\/78.80824","volume":"39","author":"A El-Jaroudi","year":"1991","unstructured":"El-Jaroudi, A., Makhoul, J.: Discrete all-pole modeling. IEEE Trans. Signal Process. 39(2), 411\u2013423 (1991)","journal-title":"IEEE Trans. Signal Process."},{"issue":"1","key":"12_CR18","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/0167-6393(93)90019-H","volume":"12","author":"C Ma","year":"1993","unstructured":"Ma, C., Kamp, Y., Willems, L.F.: Robust signal selection for linear prediction analysis of voiced speech. Speech Commun. 12(1), 69\u201381 (1993)","journal-title":"Speech Commun."},{"issue":"5","key":"12_CR19","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.specom.2008.12.005","volume":"51","author":"C Magi","year":"2009","unstructured":"Magi, C., Pohjalainen, J.: Stabilised weighted linear prediction. Speech Commun. 51(5), 401\u2013411 (2009)","journal-title":"Speech Commun."},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Airaksinen, M., Story, B., Alku, P.: Quasi closed phase analysis for glottal inverse filtering. In: 14th Annual Conference of the International Speech Communication Association, pp. 143\u2013147. ISCA, Lyon (2013)","DOI":"10.21437\/Interspeech.2013-55"},{"issue":"3","key":"12_CR21","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1109\/TASLP.2013.2294585","volume":"22","author":"M Airaksinen","year":"2014","unstructured":"Airaksinen, M., Raitio, T., Story, B., et al.: Quasi closed phase glottal inverse filtering analysis with weighted linear prediction. IEEE Trans. Audio Speech Lang. Process. 22(3), 596\u2013607 (2014)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"3","key":"12_CR22","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1109\/TASL.2011.2170835","volume":"20","author":"T Drugman","year":"2012","unstructured":"Drugman, T., Thomas, M., Gudnason, J., et al.: Detection of glottal closure instants from speech signal: a quantitative review. IEEE Trans. Audio Speech Lang. Process. 20(3), 994\u20131006 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Sofoklis, K., Okko, R., Pavvo, A.: Evaluation of spectral tilt measures for sentence prominence under different noise conditions. In: Proceedings of Interspeech, pp. 3211\u20133215. ISCA, Stockholm (2017)","DOI":"10.21437\/Interspeech.2017-1237"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Lopez, A.R., Seshadri, S., Juvela, L., et al.: Speaking style conversion from normal to Lombard speech using a glottal vocoder and Bayesian GMMs. In: Proceedings of Interspeech, pp. 1363\u20131367. ISCA, Stockholm (2017)","DOI":"10.21437\/Interspeech.2017-400"},{"issue":"3\u20134","key":"12_CR25","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/S0925-2312(97)00161-6","volume":"15","author":"AC Tsoi","year":"1997","unstructured":"Tsoi, A.C., Back, A.: Discrete time recurrent neural network architectures: a unifying review. Neurocomputing 15(3\u20134), 183\u2013223 (1997)","journal-title":"Neurocomputing"},{"key":"12_CR26","unstructured":"So\u0142oducha, M., Raake, A., Kettler, F., Voigt, P.: Lombard speech database for German language. In: Proceedings of DAGA, Aachen (2016)"},{"issue":"4","key":"12_CR27","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.specom.2013.01.001","volume":"55","author":"M Cooke","year":"2013","unstructured":"Cooke, M., Mayo, C., Valentini-Botinhao, C., et al.: Evaluating the intelligibility benefit of speech modifications in known noise conditions. Speech Commun. 55(4), 572\u2013585 (2013)","journal-title":"Speech Commun."},{"key":"12_CR28","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1109\/TAU.1969.1162058","volume":"17","author":"EH Rothauser","year":"1969","unstructured":"Rothauser, E.H.: IEEE recommended practice for speech quality measurements. IEEE Trans. Audio Electroacoust. 17, 225\u2013246 (1969)","journal-title":"IEEE Trans. Audio Electroacoust."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05716-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T11:02:09Z","timestamp":1775300529000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05716-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,11]]},"ISBN":["9783030057152","9783030057169"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05716-9_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,11]]},"assertion":[{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/mmm2019.iti.gr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double blind for full papers and workshop papers, single blind for other paper types","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"204","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"96","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.67","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"6 demonstration papers, 5 industry papers, 6 workshop papers, and 6 Video Browser Showdown papers were also accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}