{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T09:52:39Z","timestamp":1775296359085,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2018,12,5]],"date-time":"2018-12-05T00:00:00Z","timestamp":1543968000000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s11042-018-6947-8","type":"journal-article","created":{"date-parts":[[2018,12,5]],"date-time":"2018-12-05T01:02:57Z","timestamp":1543971777000},"page":"15483-15505","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A near-end listening enhancement system by RNN-based noise cancellation and speech modification"],"prefix":"10.1007","volume":"78","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":"Xiaochen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,5]]},"reference":[{"issue":"22","key":"6947_CR1","doi-asserted-by":"publisher","first-page":"23661","DOI":"10.1007\/s11042-016-4145-0","volume":"76","author":"AB Aicha","year":"2017","unstructured":"Aicha AB (2017) Noise estimation for speech enhancement algorithms with post-smoothness processor incorporating global posterior SNR. Multimed Tools Appl 76(22):23661\u201323678","journal-title":"Multimed Tools Appl"},{"key":"6947_CR2","first-page":"5","volume":"s3","author":"ANSI","year":"1997","unstructured":"ANSI (1997) American national standard methods for calculation of the speech intelligibility index. American National Standard Institute Inc s3:5\u20131997","journal-title":"American National Standard Institute Inc"},{"key":"6947_CR3","doi-asserted-by":"crossref","unstructured":"Ballou G (2015) Handbook for sound engineers Focal Press","DOI":"10.4324\/9780203758281"},{"key":"6947_CR4","doi-asserted-by":"crossref","unstructured":"Chen Z, Luo Y, Mesgarani N (2017) Deep attractor network for single-microphone speaker separation. In: IEEE international conference on acoustics, speech and signal processing, pp 246\u2013250","DOI":"10.1109\/ICASSP.2017.7952155"},{"issue":"2, SI","key":"6947_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":"6947_CR6","doi-asserted-by":"crossref","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, Delft"},{"key":"6947_CR7","unstructured":"ETSI (2014) TS 103 224 (V1.2.1): Speech and multimedia Transmission Quality (STQ); A sound field reproduction method for terminal testing including a background noise databas. Standard, ETSI"},{"key":"6947_CR8","unstructured":"ETSI (2015) EG 202 396-1 (V1.6.1): Speech processing, transmission and quality aspects (STQ); Speech quality performance in the presence of background noise; Part 1: Background noise simulation technique and background noise databas. Standard, ETSI"},{"issue":"2","key":"6947_CR9","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1016\/j.sigpro.2012.08.013","volume":"93","author":"NV George","year":"2013","unstructured":"George NV, Panda G (2013) Advances in active noise control: a survey, with emphasis on recent nonlinear techniques. Signal Process 93(2):363\u2013377","journal-title":"Signal Process"},{"key":"6947_CR10","unstructured":"Han Y, Lee K (2016) Convolutional neural network with multiple-width frequency-delta data augmentation for acoustic scene classification. IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events"},{"key":"6947_CR11","volume-title":"800: Methods for subjective determination of transmission quality","author":"P ITU-T","year":"1996","unstructured":"ITU-T P (1996) 800: Methods for subjective determination of transmission quality. International Telecommunication Union, Geneva"},{"key":"6947_CR12","doi-asserted-by":"crossref","unstructured":"Jokinen E, Remes U, Alku P (2016) The use of read versus conversational lombard speech in spectral tilt modeling for intelligibility enhancement in near-end noise conditions. In: Proceedings of the 17th annual conference of the international speech communication association, pp 2771\u20132775","DOI":"10.21437\/Interspeech.2016-143"},{"issue":"10","key":"6947_CR13","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":"6947_CR14","doi-asserted-by":"crossref","unstructured":"Kakouros S, Rasanen O, Alku P (2017) Evaluation of spectral tilt measures for sentence prominence under different noise conditions. In: Proceedings of the annual conference of the international speech communication association, vol 2017, pp 3211\u20133215","DOI":"10.21437\/Interspeech.2017-1237"},{"issue":"8","key":"6947_CR15","doi-asserted-by":"publisher","first-page":"1694","DOI":"10.1109\/TASLP.2017.2714424","volume":"25","author":"S Khademi","year":"2017","unstructured":"Khademi S, Hendriks RC, Kleijn WB (2017) Intelligibility enhancement based on mutual information. IEEE\/ACM Trans Audio Speech Language Process 25 (8):1694\u20131708","journal-title":"IEEE\/ACM Trans Audio Speech Language Process"},{"issue":"2","key":"6947_CR16","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 P, Sauert B, Vary P (2015) Optimizing speech intelligibility in a noisy environment: a unified view. IEEE Signal Process Mag 32(2):43\u201354","journal-title":"IEEE Signal Process Mag"},{"key":"6947_CR17","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 18th annual conference of the international speech communication association, pp 1973\u20131977","DOI":"10.21437\/Interspeech.2017-1157"},{"key":"6947_CR18","doi-asserted-by":"crossref","unstructured":"Koutsogiannaki M, Stylianou Y (2014) Simple and artefact-free spectral modifications for enhancing the intelligibility of casual speech. In: IEEE international conference on acoustics, speech and signal processing, pp 4648\u20134652","DOI":"10.1109\/ICASSP.2014.6854483"},{"issue":"6","key":"6947_CR19","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1109\/5.763310","volume":"87","author":"SM Kuo","year":"1999","unstructured":"Kuo SM, Morgan DR (1999) Active noise control: a tutorial review. Proc IEEE 87(6):943\u2013973","journal-title":"Proc IEEE"},{"issue":"4","key":"6947_CR20","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1109\/TASSP.1978.1163100","volume":"26","author":"R Niederjohn","year":"1978","unstructured":"Niederjohn R, Grotelueschen J (1978) Speech intelligibility enhancement in a power generating noise environment. IEEE Trans Acoust Speech Signal Process 26(4):378\u2013380","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"4","key":"6947_CR21","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1109\/5.842996","volume":"88","author":"T Painter","year":"2000","unstructured":"Painter T, Spanias A (2000) Perceptual coding of digital audio. Proc IEEE 88(4):451\u2013515","journal-title":"Proc IEEE"},{"issue":"2","key":"6947_CR22","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":"6947_CR23","doi-asserted-by":"crossref","unstructured":"Piczak KJ (2015) Environmental sound classification with convolutional neural networks. In: IEEE 25th international workshop on machine learning for signal processing, pp 1\u20136","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"6947_CR24","doi-asserted-by":"crossref","unstructured":"Priyanka SS (2017) A review on adaptive beamforming techniques for speech enhancement. In: Innovations in power and advanced computing technologies, pp 1\u20136","DOI":"10.1109\/IPACT.2017.8245048"},{"key":"6947_CR25","volume-title":"Discrete cosine transform: algorithms, advantages, applications","author":"KR Rao","year":"2014","unstructured":"Rao KR, Yip P (2014) Discrete cosine transform: algorithms, advantages, applications. Academic Press, Cambridge"},{"key":"6947_CR26","doi-asserted-by":"crossref","unstructured":"Salamon J, Jacoby C, Bello JP (2014) A dataset and taxonomy for urban sound research. In: Proceedings of the 22nd ACM international conference on multimedia, pp 1041\u20131044","DOI":"10.1145\/2647868.2655045"},{"key":"6947_CR27","doi-asserted-by":"crossref","unstructured":"Sauert B, Vary P (2006) Near end listening enhancement: speech intelligibility improvement in noisy environments. In: IEEE international conference on acoustics speech and signal processing, vol 1, pp I\u2013I","DOI":"10.1109\/ICASSP.2006.1660065"},{"issue":"10","key":"6947_CR28","doi-asserted-by":"publisher","first-page":"1541","DOI":"10.1109\/5.326413","volume":"82","author":"AS Spanias","year":"1994","unstructured":"Spanias AS (1994) Speech coding: a tutorial review. Proc IEEE 82(10):1541\u20131582","journal-title":"Proc IEEE"},{"issue":"4","key":"6947_CR29","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"},{"issue":"4","key":"6947_CR30","first-page":"412","volume":"16","author":"IB Thomas","year":"1968","unstructured":"Thomas IB, Niederjohn RJ (1968) Enhancement of speech intelligibility at high noise levels by filtering and clipping. J Audio Eng Soc 16(4):412\u2013415","journal-title":"J Audio Eng Soc"},{"issue":"3","key":"6947_CR31","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 HJ (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":"6947_CR32","unstructured":"Wang D, Zhang X (2015) THCHS-30: a free chinese speech corpus. Computer Science"},{"key":"6947_CR33","doi-asserted-by":"crossref","unstructured":"West NE, O\u2019Shea T (2017) Deep architectures for modulation recognition. In: IEEE international symposium on dynamic spectrum access networks, pp 1\u20136","DOI":"10.1109\/DySPAN.2017.7920754"},{"issue":"12","key":"6947_CR34","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1109\/TMM.2018.2838320","volume":"20","author":"C Yan","year":"2018","unstructured":"Yan C, Xie H, Chen J, Zha Z, Hao X, Zhang Y, Dai Q (2018) A fast uyghur text detector for complex background images. IEEE Trans Multimedia 20 (12):3389\u20133398. https:\/\/doi.org\/10.1109\/TMM.2018.2838320 ISSN=1520\u20139210","journal-title":"IEEE Trans Multimedia"},{"issue":"1","key":"6947_CR35","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1109\/TITS.2017.2749977","volume":"19","author":"C Yan","year":"2018","unstructured":"Yan C, Xie H, Liu S, Yin J, Zhang Y, Dai Q (2018) Effective uyghur language text detection in complex background images for traffic prompt identification. IEEE Trans Intell Transp Syst 19(1):220\u2013229","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"1","key":"6947_CR36","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1109\/TITS.2017.2749965","volume":"19","author":"C Yan","year":"2018","unstructured":"Yan C, Xie H, Yang D, Yin J, Zhang Y, Dai Q (2018) Supervised hash coding with deep neural network for environment perception of intelligent vehicles. IEEE Trans Intell Transp Syst 19(1):284\u2013295","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"5","key":"6947_CR37","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1109\/LSP.2014.2310494","volume":"21","author":"C Yan","year":"2014","unstructured":"Yan C, Zhang Y, Xu J, Dai F, Li L, Dai Q, Wu F (2014) A highly parallel framework for HEVC coding unit partitioning tree decision on many-core processors. IEEE Signal Process Lett 21(5):573\u2013576","journal-title":"IEEE Signal Process Lett"},{"issue":"12","key":"6947_CR38","doi-asserted-by":"publisher","first-page":"2077","DOI":"10.1109\/TCSVT.2014.2335852","volume":"24","author":"C Yan","year":"2014","unstructured":"Yan C, Zhang Y, Xu J, Dai F, Zhang J, Dai Q, Wu F (2014) Efficient parallel framework for HEVC motion estimation on many-core processors. IEEE Trans Circuits Syst Video Technol 24(12):2077\u20132089","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"3","key":"6947_CR39","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1109\/JAS.2017.7510508","volume":"4","author":"D Yu","year":"2017","unstructured":"Yu D, Li J (2017) Recent progresses in deep learning based acoustic models. IEEE\/CAA Journal of Automatica Sinica 4(3):396\u2013409","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"6947_CR40","doi-asserted-by":"crossref","unstructured":"Zoril\u0103 TC, Kandia V, Stylianou Y (2012) Speech-in-noise intelligibility improvement based on spectral shaping and dynamic range compression. In: Proceedings of the 13th annual conference of the international speech communication association, pp 634\u2013637","DOI":"10.21437\/Interspeech.2012-197"},{"issue":"1","key":"6947_CR41","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1121\/1.4973533","volume":"141","author":"TC Zoril\u0103","year":"2017","unstructured":"Zoril\u0103 TC, Stylianou Y, Flanagan S, Moore BC (2017) Evaluation of near-end speech enhancement under equal-loudness constraint for listeners with normal-hearing and mild-to-moderate hearing loss. J Acoust Soc Am 141(1):189\u2013196","journal-title":"J Acoust Soc Am"},{"issue":"10","key":"6947_CR42","doi-asserted-by":"publisher","first-page":"1808","DOI":"10.1109\/TASLP.2016.2585864","volume":"24","author":"TC Zoril\u0103","year":"2016","unstructured":"Zoril\u0103 TC, Stylianou Y, Ishihara T, Akamine M (2016) Near and far field speech-in-noise intelligibility improvements based on a time-frequency energy reallocation approach. IEEE\/ACM Trans Audio Speech, and Language Process 24(10):1808\u20131818","journal-title":"IEEE\/ACM Trans Audio Speech, and Language Process"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6947-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6947-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6947-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T09:06:59Z","timestamp":1775293619000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6947-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,5]]},"references-count":42,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["6947"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6947-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,5]]},"assertion":[{"value":"12 June 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 November 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}