{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T08:35:16Z","timestamp":1725698116845},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"27-28","license":[{"start":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T00:00:00Z","timestamp":1585008000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T00:00:00Z","timestamp":1585008000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61801334","61801334","U1736206"],"award-info":[{"award-number":["61801334","61801334","U1736206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2017YFB1002803","2017YFB1002803","2017YFB1002803"],"award-info":[{"award-number":["2017YFB1002803","2017YFB1002803","2017YFB1002803"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1007\/s11042-020-08838-1","type":"journal-article","created":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T06:02:32Z","timestamp":1585029752000},"page":"19471-19491","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A mapping model of spectral tilt in normal-to-Lombard speech conversion for intelligibility enhancement"],"prefix":"10.1007","volume":"79","author":[{"given":"Gang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruimin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaochen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,24]]},"reference":[{"key":"8838_CR1","doi-asserted-by":"publisher","first-page":"EL523","DOI":"10.1121\/1.5042758","volume":"143","author":"N Alghamdi","year":"2018","unstructured":"Alghamdi N, Maddock S, Marxer R, Barker J, Brown GJ (2018) A corpus of audio-visual Lombard speech with frontal and profile views. J Acoust Soc Am 143:EL523\u2013EL529. [Available]: https:\/\/datashare.is.ed.ac.uk\/handle\/10283\/347","journal-title":"J Acoust Soc Am"},{"key":"8838_CR2","unstructured":"ANSI (1997) American national standard methods for calculation of the speech intelligibility index. American National Standard Institute s3.5-1997"},{"key":"8838_CR3","unstructured":"AVS (2010) Information technology - Advanced coding of audio and video - Part 10: Mobile speech and audio (GB\/T20090.10-2013). National Standards of the People\u2019s Republic of China"},{"issue":"4","key":"8838_CR4","doi-asserted-by":"publisher","first-page":"1218","DOI":"10.1109\/TSA.2005.860851","volume":"14","author":"J Chen","year":"2006","unstructured":"Chen J, Benesty J, Huang Y, Doclo S (2006) New insights into the noise reduction Wiener filter. IEEE\/ACM Trans Audio Speech Language Process 14 (4):1218\u20131234","journal-title":"IEEE\/ACM Trans Audio Speech Language Process"},{"issue":"2, SI","key":"8838_CR5","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.csl.2013.08.003","volume":"28","author":"M Cooke","year":"2014","unstructured":"Cooke M, King S, Garnier M, Aubanel V (2014) The listening talker: a review of human and algorithmic context-induced modifications of speech. Comput Speech Lang 28(2, SI):543\u2013571","journal-title":"Comput Speech Lang"},{"key":"8838_CR6","doi-asserted-by":"crossref","unstructured":"Cooke M, Mayo C, Valentini-Botinhao C (2013) Intelligibility-enhancing speech modifications: the hurricane challenge. In: Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 3552\u20133556","DOI":"10.21437\/Interspeech.2013-764"},{"key":"8838_CR7","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988157","volume-title":"Deep learning: methods and applications","author":"L Deng","year":"2014","unstructured":"Deng L, Yu D (2014) Deep learning: methods and applications. Now Publishers Inc., Boston"},{"key":"8838_CR8","unstructured":"Ellis D (2003) Dynamic time warp (DTW) in MATLAB. [Available]: http:\/\/www.ee.columbia.edu\/~dpwe\/resources\/matlab\/dtw\/"},{"key":"8838_CR9","doi-asserted-by":"crossref","unstructured":"Gao L, Hu R, Yang Y (2014) A spatial priority based scalable audio coding. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp 3670\u20133674","DOI":"10.1109\/ICASSP.2014.6854286"},{"issue":"2, SI","key":"8838_CR10","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1016\/j.csl.2013.07.005","volume":"28","author":"M Garnier","year":"2014","unstructured":"Garnier M, Henrich N (2014) Speaking in noise: How does the Lombard effect improve acoustic contrasts between speech and ambient noise?. Comput Speech Lang 28(2, SI):580\u2013597","journal-title":"Comput Speech Lang"},{"issue":"10","key":"8838_CR11","doi-asserted-by":"publisher","first-page":"759","DOI":"10.17743\/jaes.2018.0041","volume":"66","author":"R Huber","year":"2018","unstructured":"Huber R, Ooster J, Meyer BT (2018) Single-ended speech quality prediction based on automatic speech recognition. J Audio Eng Soc 66(10):759\u2013769","journal-title":"J Audio Eng Soc"},{"key":"8838_CR12","unstructured":"ITU-T R (1996) P. 800 Methods for subjective determination of transmission quality"},{"key":"8838_CR13","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.specom.2015.09.013","volume":"76","author":"TL Jensen","year":"2016","unstructured":"Jensen TL, Giacobello D, van Waterschoot T, Christensen MG (2016) Fast algorithms for high-order sparse linear prediction with applications to speech processing. Speech Comm 76:143\u2013156","journal-title":"Speech Comm"},{"issue":"4","key":"8838_CR14","doi-asserted-by":"publisher","first-page":"EL327","DOI":"10.1121\/1.4979162","volume":"141","author":"E Jokinen","year":"2017","unstructured":"Jokinen E, Alku P (2017) Estimating the spectral tilt of the glottal source from telephone speech using a deep neural network. J Acoust Soc Am 141(4):EL327\u2013EL330","journal-title":"J Acoust Soc Am"},{"key":"8838_CR15","doi-asserted-by":"crossref","unstructured":"Jokinen E, Remes U, Alku P (2015) Comparison of Gaussian process regression and Gaussian mixture models in spectral tilt modelling for intelligibility enhancement of telephone speech. In: Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 85\u201389","DOI":"10.21437\/Interspeech.2015-32"},{"issue":"10","key":"8838_CR16","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 (2017) Intelligibility enhancement of telephone speech using Gaussian process regression for normal-to-Lombard spectral tilt conversion. IEEE\/ACM Trans Audio Speech Language Process 25(10):1985\u20131996","journal-title":"IEEE\/ACM Trans Audio Speech Language Process"},{"key":"8838_CR17","doi-asserted-by":"crossref","unstructured":"Jokinen E, Remes U, Takanen M, Paloma\u0307ki K, Kurimo M, Alku P (2014) Spectral tilt modelling with GMMs for intelligibility enhancement of narrowband telephone speech. In: Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 2036\u20132040","DOI":"10.1109\/IWAENC.2014.6953999"},{"key":"8838_CR18","doi-asserted-by":"crossref","unstructured":"Junqua JC (1991) The influence of psychoacoustic and psycholinguistic factors on listener judgments of intelligibility of normal and Lombard speech. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol 1, pp 361\u2013364","DOI":"10.1109\/ICASSP.1991.150351"},{"key":"8838_CR19","doi-asserted-by":"crossref","unstructured":"Junqua JC, Fincke S, Field K (1999) The Lombard effect: A reflex to better communicate with others in noise. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp 2083\u20132086","DOI":"10.1109\/ICASSP.1999.758343"},{"key":"8838_CR20","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.specom.2018.08.002","volume":"103","author":"S Kakouros","year":"2018","unstructured":"Kakouros S, R\u00e4s\u00e4nen O, Alku P (2018) Comparison of spectral tilt measures for sentence prominence in speech-effects of dimensionality and adverse noise conditions. Speech Comm 103:11\u201326","journal-title":"Speech Comm"},{"issue":"2","key":"8838_CR21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/MSP.2014.2365594","volume":"32","author":"WB Kleijn","year":"2015","unstructured":"Kleijn WB, Crespo JB, Hendriks RC, Petkov PN, Sauert B, Vary P (2015) Optimizing speech intelligibility in a noisy environment: a unified view. IEEE Signal Proc Mag 32(2):43\u201354","journal-title":"IEEE Signal Proc Mag"},{"issue":"1\/2","key":"8838_CR22","doi-asserted-by":"publisher","first-page":"117","DOI":"10.17743\/jaes.2016.0047","volume":"65","author":"I Kodrasi","year":"2017","unstructured":"Kodrasi I, Cauchi B, Goetze S, Doclo S (2017) Instrumental and perceptual evaluation of dereverberation techniques based on robust acoustic multichannel equalization. J Audio Eng Soc 65(1\/2):117\u2013129","journal-title":"J Audio Eng Soc"},{"key":"8838_CR23","doi-asserted-by":"crossref","unstructured":"Koutsogiannaki M, Francois H, Choo K, Oh E (2017) Real-time modulation enhancement of temporal envelopes for increasing speech intelligibility. In: Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 1973\u20131977","DOI":"10.21437\/Interspeech.2017-1157"},{"key":"8838_CR24","doi-asserted-by":"crossref","unstructured":"Koutsogiannaki M, Stylianou Y (2014) Simple and artefact-free spectral modifications for enhancing the intelligibility of casual speech. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","DOI":"10.1109\/ICASSP.2014.6854483"},{"key":"8838_CR25","unstructured":"Lombard E (1911) Le signe de l\u2019elevation de la voix. Ann. Mal. de L\u2019Oreille et du Larynx pp. 101\u2013119"},{"key":"8838_CR26","doi-asserted-by":"crossref","unstructured":"Lo\u0307pez AR, Seshadri S, Juvela L, Ra\u0307sa\u0307nen O, Alku P (2017) Speaking style conversion from normal to Lombard speech using a glottal vocoder and Bayesian GMMs. In: Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 1363\u20131367","DOI":"10.21437\/Interspeech.2017-400"},{"issue":"12","key":"8838_CR27","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 (2009) The contribution of changes in f0 and spectral tilt to increased intelligibility of speech produced in noise. Speech Comm 51(12):1253\u20131262","journal-title":"Speech Comm"},{"issue":"2","key":"8838_CR28","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1109\/TASLP.2014.2384271","volume":"23","author":"PN Petkov","year":"2015","unstructured":"Petkov PN, Kleijn WB (2015) Spectral dynamics recovery for enhanced speech intelligibility in noise. IEEE\/ACM Trans Audio, Speech, Language Process 23(2):327\u2013338","journal-title":"IEEE\/ACM Trans Audio, Speech, Language Process"},{"key":"8838_CR29","volume-title":"Theory and applications of digital speech processing","author":"LR Rabiner","year":"2011","unstructured":"Rabiner LR, Schafer RW (2011) Theory and applications of digital speech processing. Pearson, Upper Saddle River"},{"key":"8838_CR30","doi-asserted-by":"crossref","unstructured":"Schepker H, Rennies J, Doclo S (2013) Improving speech intelligibility in noise by SII-dependent preprocessing using frequency-dependent amplification and dynamic range compression. In: Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 3577\u20133581","DOI":"10.21437\/Interspeech.2013-769"},{"key":"8838_CR31","unstructured":"So\u0142oducha M, Raake A, Kettler F, Voigt P (2016) Lombard speech database for German language. In: Proceedings of German Annual Conference on Acoustics (DAGA). [Available]: http:\/\/spandh.dcs.shef.ac.uk\/avlombard\/"},{"issue":"4","key":"8838_CR32","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1016\/j.csl.2013.11.003","volume":"28","author":"CH Taal","year":"2014","unstructured":"Taal CH, Hendriks RC, Heusdens R (2014) Speech energy redistribution for intelligibility improvement in noise based on a perceptual distortion measure. Comput Speech Lang 28(4):858\u2013872","journal-title":"Comput Speech Lang"},{"key":"8838_CR33","unstructured":"Taal CH, Jensen J (2013) SII-Based speech preprocessing for intelligibility improvement in noise. In: Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 3582\u20133586"},{"issue":"3","key":"8838_CR34","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga A, Steeneken H (1993) Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Comm 12(3):247\u2013251","journal-title":"Speech Comm"},{"key":"8838_CR35","doi-asserted-by":"crossref","unstructured":"Wang X, Wang Y, Hang B (2013) Application of AVS-p10 mobile speech and audio coding in social multimedia. In: Proceedings of the International Conference on Internet Multimedia Computing and Service (ICIMCS), pp 101\u2013104","DOI":"10.1145\/2499788.2499839"},{"key":"8838_CR36","doi-asserted-by":"crossref","unstructured":"Wen Z, Tao Z, Liang Z, Hai Z (2010) Performance analysis and evaluation of AVS-m audio coding. In: Proceedings of the International Conference on Audio, Language and Image Processing, Proceedings (ICALIP), pp 31\u201336","DOI":"10.1109\/ICALIP.2010.5685024"},{"key":"8838_CR37","doi-asserted-by":"crossref","unstructured":"Zhang R, Hu R, Li G, Wang X (2019) Spectral tilt estimation for speech intelligibility enhancement using RNN based on all-pole model. In: Proceedings of the International Conference on Multimedia Modeling (MMM), pp 144\u2013156","DOI":"10.1007\/978-3-030-05716-9_12"},{"key":"8838_CR38","doi-asserted-by":"crossref","unstructured":"Zorila\u0307 TC, Kandia V, Stylianou Y (2012) Speech-in-noise intelligibility improvement based on spectral shaping and dynamic range compression. In: Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 634\u2013637","DOI":"10.21437\/Interspeech.2012-197"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-08838-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-020-08838-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-08838-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T16:03:24Z","timestamp":1666195404000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-020-08838-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,24]]},"references-count":38,"journal-issue":{"issue":"27-28","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["8838"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-08838-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,24]]},"assertion":[{"value":"29 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}