{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T19:55:12Z","timestamp":1774468512725,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2014,12,1]],"date-time":"2014-12-01T00:00:00Z","timestamp":1417392000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Spanish Ministry of Economy and Competitiveness","award":["TEC2012-38939-C03-03"],"award-info":[{"award-number":["TEC2012-38939-C03-03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/taslp.2014.2361022","type":"journal-article","created":{"date-parts":[[2014,10,1]],"date-time":"2014-10-01T18:59:07Z","timestamp":1412189947000},"page":"2101-2111","source":"Crossref","is-referenced-by-count":11,"title":["Enhancing the Intelligibility of Statistically Generated Synthetic Speech by Means of Noise-Independent Modifications"],"prefix":"10.1109","volume":"22","author":[{"given":"Daniel","family":"Erro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tudor-Catalin","family":"Zorila","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannis","family":"Stylianou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-1.1.325"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.01.001"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639193"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-198","article-title":"Implementation of simple spectral techniques to enhance the intelligibility of speech using a harmonic model","author":"erro","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"635","DOI":"10.21437\/Interspeech.2012-197","article-title":"Speech-in-noise intelligibility improvement based on spectral shaping and dynamic range compression","author":"zoril?","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"key":"ref36","first-page":"3552","article-title":"Intelligibility-enhancing speech modifications: The Hurricane Challenge","author":"cooke","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref35","first-page":"3557","article-title":"Statistical synthesizer with embedded prosodic and spectral modifications to generate highly intelligible speech in noise","author":"erro","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1002\/scj.20354"},{"key":"ref62","first-page":"225","article-title":"IEEE recommended practices for speech quality measurements (appendix: Harvard sentences)","volume":"ae 17","year":"1969","journal-title":"IEEE Trans Audio Electroacoust"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1121\/1.2142744"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"823","DOI":"10.21437\/Eurospeech.1999-213","article-title":"Synthesis of regional English using a keyword lexicon","author":"fitt","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1969.1162021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1121\/1.1861713"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-196","article-title":"Mel cepstral coefficient modification based on the glimpse proportion measure for improving the intelligibility of HMM-generated synthetic speech in noise","author":"valentini-botinhao","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref65","article-title":"Methods for the calculation of the speech intelligibility index","volume":"s3 5?1997","year":"1997","journal-title":"ANSI"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"1837","DOI":"10.21437\/Interspeech.2011-42","article-title":"Can objective measures predict the intelligibility of modified HMM-based synthetic speech in noise?","author":"valentini-botinhao","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162824"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.21437\/Interspeech.2011-32","article-title":"Continuous control of the degree of articulation in HMM-based speech synthesis","author":"picart","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415101"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.2751257"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1708","DOI":"10.21437\/Interspeech.2012-467","article-title":"Effect of prosodic changes on speech intelligibility","author":"mayo","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"579","DOI":"10.21437\/Interspeech.2012-177","article-title":"Can modified casual speech reach the intelligibility of clear speech?","author":"koutsogiannaki","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref24","article-title":"Assessing the intelligibility impact of vowel space expansion via clear speech-inspired frequency warping","author":"godoy","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref23","first-page":"7","article-title":"Does reading clearly produce the same acoustic-phonetic modifications as spontaneous speech in a clear speaking style?","author":"hazan","year":"2010","journal-title":"Proc DiSS-LPSS"},{"key":"ref26","first-page":"4061","article-title":"A speech processing strategy for intelligibility improvement in noise based on a perceptual distortion measure","author":"taal","year":"2012","journal-title":"Proc ICASSP"},{"key":"ref25","first-page":"1844","article-title":"Near end listening enhancement optimized with respect to speech intelligibility index","author":"sauert","year":"2009","journal-title":"Proc EUSIPCO"},{"key":"ref50","first-page":"121","author":"mcaulay","year":"1995"},{"key":"ref51","author":"valentini-botinhao","year":"2013","journal-title":"Intelligibility enhancement of synthetic speech in noise"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.03.005"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.1997.628419"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/89.365380"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/S0167-6393(02)00095-X","article-title":"Speech processing for the hearing-impaired: Successes, failures, and implications for speech mechanisms","volume":"41","author":"moore","year":"2003","journal-title":"Speech Commun"},{"key":"ref55","first-page":"49","article-title":"Spectral contrast enhancement of speech in noise for listeners with sensorineural hearing impairment: Effects on intelligibility, quality, and response times","volume":"30","author":"baer","year":"1993","journal-title":"J Rehab Res Dev"},{"key":"ref54","first-page":"43","article-title":"Cue-enhancement strategies for natural VCV and sentence materials presented in noise","volume":"9","author":"hazan","year":"1996","journal-title":"Speech Hearing Lang Phon Linguist Univ College London"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1121\/1.1908510"},{"key":"ref52","author":"miller","year":"1981","journal-title":"Perspectives on the Study of Speech"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.07.002"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"2610","DOI":"10.21437\/Interspeech.2010-257","article-title":"Glottal-based analysis of the Lombard effect","author":"drugman","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref40","first-page":"455","article-title":"Multi-space probability distribution HMM","volume":"e85 d","author":"tokuda","year":"2002","journal-title":"IEICE Trans Inf Syst"},{"key":"ref12","first-page":"87","article-title":"The role of durational changes in the lombard speech advantage","author":"villegas","year":"2012","journal-title":"Proc Listening Talker Workshop"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.21437\/Interspeech.2012-417","article-title":"Unsupervised acoustic analyses of normal and Lombard speech, with spectral envelope transformation to improve intelligibility","author":"godoy","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.2904.434"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.3203.600"},{"key":"ref16","author":"krause","year":"2001","journal-title":"Properties of naturally produced clear speech at normal rates and implications for intelligibility enhancement"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.1635842"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.2000788"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1016\/j.specom.2005.09.003","article-title":"Applied principles of clear and Lombard speech for automated intelligibility enhancement in noisy environments","volume":"48","author":"skowronski","year":"2006","journal-title":"Speech Commun"},{"key":"ref4","first-page":"258","article-title":"Lombard effect mimicking","author":"huang","year":"2010","journal-title":"Proc 7th ISCA Speech Synth Workshop"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"2781","DOI":"10.21437\/Interspeech.2011-696","article-title":"Analysis of HMM-based Lombard speech synthesis","author":"raitio","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1044\/jshd.1404.363"},{"key":"ref5","first-page":"101","article-title":"Le signe de l?\ufffdl\ufffdvation de la voix","volume":"37","author":"lombard","year":"1911","journal-title":"Ann Maladies Oreille Larynx Nez Pharynx"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.396660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/03637755109375042"},{"key":"ref49","first-page":"213","article-title":"Regularized estimation of cepstrum envelope from discrete frequency points","author":"capp\ufffd","year":"1995","journal-title":"Proc IEEE Workshop Appl Signal Process Audio Acoust"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.405631"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/97.841155"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"382","DOI":"10.21437\/Interspeech.2012-138","article-title":"A full-band adaptive harmonic representation of speech","author":"degottex","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref48","first-page":"97","article-title":"Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound","volume":"17","author":"boersma","year":"1993","journal-title":"Proc Inst Phon Sci Univ of Amsterdam"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-411","article-title":"Perceptual importance of the phase related information in speech","author":"saratxaga","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref42","first-page":"4728","article-title":"HNM-based <formula formulatype=\"inline\"><tex Notation=\"TeX\">${\\rm MFCC}+{\\rm F}0$<\/tex><\/formula> extractor applied to statistical speech synthesis","author":"erro","year":"2011","journal-title":"Proc ICASSP"},{"key":"ref41","author":"stylianou","year":"1996","journal-title":"Harmonic plus noise models for speech combined with statistical methods for speech and speaker modification"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283471"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"1809","DOI":"10.21437\/Interspeech.2011-35","article-title":"Improved HNM-based vocoder for statistical synthesizers","author":"erro","year":"2011","journal-title":"Proc INTERSPEECH"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/6882846\/06914585.pdf?arnumber=6914585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T23:34:30Z","timestamp":1746401670000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6914585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":66,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2014.2361022","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,12]]}}}