{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:25:31Z","timestamp":1760955931890,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,4,2]],"date-time":"2019-04-02T00:00:00Z","timestamp":1554163200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002888","name":"Beijing Municipal Commission of Education","doi-asserted-by":"publisher","award":["KM201510005007"],"award-info":[{"award-number":["KM201510005007"]}],"id":[{"id":"10.13039\/501100002888","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51477028"],"award-info":[{"award-number":["51477028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s13634-019-0618-4","type":"journal-article","created":{"date-parts":[[2019,4,2]],"date-time":"2019-04-02T15:05:36Z","timestamp":1554217536000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Multi-resolution auditory cepstral coefficient and adaptive mask for speech enhancement with deep neural network"],"prefix":"10.1186","volume":"2019","author":[{"given":"Ruwei","family":"Li","sequence":"first","affiliation":[]},{"given":"Xiaoyue","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Yanan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Dengcai","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Dong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,4,2]]},"reference":[{"issue":"2","key":"618_CR1","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"SF Boll","year":"1979","unstructured":"S.F. Boll, Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Acoust. Speech Signal Process. 27(2), 113\u2013120 (1979)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"4","key":"618_CR2","doi-asserted-by":"publisher","first-page":"1218","DOI":"10.1109\/TSA.2005.860851","volume":"14","author":"JD Chen","year":"2006","unstructured":"J.D. Chen, J. Benesty, Y.T. Huang, S. Doclo, New insights into the noise reduction Wiener filter. IEEE Trans. Audio Speech Lang. Process. 14(4), 1218\u20131234 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"618_CR3","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836","volume-title":"Speech Enhancement: Theory and Practice","author":"Loizou","year":"2007","unstructured":"Loizou, Speech Enhancement: Theory and Practice (CRC Press, New York, 2007)"},{"key":"618_CR4","doi-asserted-by":"crossref","unstructured":"RC. Henddriks, R. Heusdens, J. Jensen, MMSE based noise PSD tracking with low complexity. Proc.IEEE Int. Conf. Acoustics, Speech, Signal Process, 4466\u20134469 (2010)","DOI":"10.1109\/ICASSP.2010.5495680"},{"issue":"4","key":"618_CR5","doi-asserted-by":"publisher","first-page":"1118","DOI":"10.1109\/TASL.2011.2172425","volume":"20","author":"A Ozerov","year":"2012","unstructured":"A. Ozerov, E. Vincent, F. Bimbot, A general flexible framework for the handling of prior information in audio source separation. IEEE Trans. Audio Speech Lang. Process. 20(4), 1118\u20131133 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"10","key":"618_CR6","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1109\/TASL.2013.2270369","volume":"21","author":"N Mohammadiha","year":"2013","unstructured":"N. Mohammadiha, P. Smaragdis, A. Leijon, Supervised and unsupervised speech enhancement using non-negative matrix factorization. IEEE Trans. Audio Speech Lang. Process. 21(10), 2140\u20132151 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"618_CR7","unstructured":"L. Ruwei, B. Changchun, D. Huijing, Speech enhancement using adaptive threshold based on bi-orthogonal wavelet packet decomposition. Chin. J. Sci. Instrum. 29(10), 2135\u20132140 (2008)"},{"issue":"3","key":"618_CR8","first-page":"362","volume":"24","author":"L Ruwei","year":"2009","unstructured":"L. Ruwei, B. Changchun, D. Huijing, Speech enhancement algorithm based on wavelet transform. J Data Acquis Proc 24(3), 362\u2013368 (2009)","journal-title":"J Data Acquis Proc"},{"key":"618_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387","volume-title":"Computational Auditory Scene Analysis: Principles, Algorithms, and Applications","author":"DL Wang","year":"2006","unstructured":"D.L. Wang, G.J. Brown, Computational Auditory Scene Analysis: Principles, Algorithms, and Applications (IEEE Press, Piscataway, 2006)"},{"key":"618_CR10","unstructured":"Z. Weiqiang, G. Cong, Z. Qiao, K. Jian, H. Liang, L. Jia, T. Johnson Micheal, A speech enhancement algorithm based on computational auditory scene analysis. J Tian Jin Univ (Sci Technol) 48(8), 663\u2013669. (2015)"},{"key":"618_CR11","unstructured":"L. Wen, J. Nie, S. Liang, S. Zhang, X. Liang, Deep learning based speech separation technology and its developments. Zidonghua Xuebao\/acta Automatica Sinica 42(6), 819\u2013833 (2016)"},{"issue":"1","key":"618_CR12","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2014","unstructured":"Y. Xu, J. Du, L.R. Dai, C.H. Lee, An experimental study on speech enhancement based on deep neural networks. IEEE Signal Process Lett. 21(1), 65\u201368 (2014)","journal-title":"IEEE Signal Process Lett."},{"key":"618_CR13","first-page":"3737","volume-title":"IEEE International Conference on Acoustics Speech and Signal Processing","author":"F Weninger","year":"2014","unstructured":"F. Weninger, F. Eyben, B. Schuller, in IEEE International Conference on Acoustics Speech and Signal Processing. Single-channel speech separation with memory-enhanced recurrent neural networks (IEEE Press, Florence, 2014), pp. 3737\u20133741"},{"issue":"1","key":"618_CR14","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","volume":"23","author":"Y Xu","year":"2015","unstructured":"Y. Xu, J. Du, L.R. Dai, et al., A regression approach to soeech enhancement based on deep neural network. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(1), 7\u201319 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"12","key":"618_CR15","doi-asserted-by":"publisher","first-page":"2136","DOI":"10.1109\/TASLP.2015.2468583","volume":"23","author":"PS Huang","year":"2015","unstructured":"P.S. Huang, M. Kim, M. Hasegawa-Johnson, P. Smaragdis, Joint optimization of masks and deep recurrent neural networks for monaural source separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(12), 2136\u20132147 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"618_CR16","first-page":"499","volume-title":"IEEE International Conference on Acoustics Speech and Signal Processing","author":"TT Vu","year":"2016","unstructured":"T.T. Vu, B. Bigot, E.S. Chng, in IEEE International Conference on Acoustics Speech and Signal Processing. Combining non-negative matrix facorization and deep neural networks for speech enhancement and automatic speech recognition (IEEE Press, Shanghai, 2016), pp. 499\u2013503"},{"key":"618_CR17","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.specom.2016.10.008","volume":"85","author":"R Li","year":"2016","unstructured":"R. Li, Y. Liu, Y. Shi, W. Cui, ILMSAF based speech enhancement with DNN and noise classification. Speech Comm. 85, 53\u201370 (2016)","journal-title":"Speech Comm."},{"issue":"7","key":"618_CR18","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1109\/TASL.2013.2250961","volume":"21","author":"Y Wang","year":"2013","unstructured":"Y. Wang, D.L. Wang, Towards scaling up classification-based speech separation. IEEE Trans. Audio Speech Lang. Process. 21(7), 1381\u20131390 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"618_CR19","doi-asserted-by":"crossref","unstructured":"A. Narayanan, D.L. Wang, Ideal Ration Mask Estimation on Using Deep Neural Networks for Robust Speech Recognition (IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, 2013), pp. 1520\u20136149","DOI":"10.1109\/ICASSP.2013.6639038"},{"issue":"12","key":"618_CR20","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","volume":"22","author":"YX Wang","year":"2014","unstructured":"Y.X. Wang, A. Narayanan, D.L. Wang, On training targets for supervised speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(12), 1849\u20131858 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"618_CR21","volume-title":"IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP)","author":"J Chen","year":"2014","unstructured":"J. Chen, Y. Wang, D.L. Wang, in IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP). A feature study for classification-based speech separation at very low signal-to noise ratio (2014)"},{"key":"618_CR22","volume-title":"IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP)","author":"H-W Tseng","year":"2015","unstructured":"H.-W. Tseng, M. Hong, Z.-Q. Luo, in IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP). Combing sparse NMF with neural network: a new classification-based approach for speech enhancement (2015)"},{"key":"618_CR23","volume-title":"The 9th International Congress on Image and Signal Processing BioMedical Engineering and Information (CISP-BMEI2016)","author":"Y Jiang","year":"2016","unstructured":"Y. Jiang, W. Li, Y. Zu, in The 9\n                           th International Congress on Image and Signal Processing BioMedical Engineering and Information (CISP-BMEI2016). A DNN parameter mask for the binaural reverberant speech segregation (2016)"},{"key":"618_CR24","first-page":"1203","volume-title":"Interspeech","author":"L Xu","year":"2017","unstructured":"L. Xu, J. Li, Y. Yan, in Interspeech. Ideal ratio mask estimation using deep neural networks for monaural speech segregation in noisy reverberant conditions (2017), pp. 1203\u20131207"},{"key":"618_CR25","doi-asserted-by":"crossref","unstructured":"H. Zhang, X. Zhang, G. Gao, in Interspeech. Multi-target ensemble learning for monaural speech separation [C]\/\/INTERSPEECH. 1958-62, 2017","DOI":"10.21437\/Interspeech.2017-240"},{"key":"618_CR26","doi-asserted-by":"crossref","unstructured":"L. Sun, J. Du, L.-R. Dai, C.-H. Lee, Multiple-Target Deep Learning for LSTM-RNN Based Speech Enhancement (Hands-free Speech Communications and Microphone Arrays, HSCMA, 2017)","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"618_CR27","volume-title":"Matlab Time Frequency Analysis Technology and its Application","author":"G Zhexue","year":"2006","unstructured":"G. Zhexue, C. Zhongsheng, Matlab Time Frequency Analysis Technology and its Application (People's post and Telecommunications Press, Beijing, 2006)"},{"key":"618_CR28","first-page":"1","volume-title":"Proc. Signal Processing, Communications and Computing (ICSPCC)","author":"YW Yang","year":"2015","unstructured":"Y.W. Yang, Y. Jiang, R.S. Liu, et al., in Proc. Signal Processing, Communications and Computing (ICSPCC). A realtime analysis\/synthesis Gammatone filterbank (2015), pp. 1\u20136"},{"key":"618_CR29","doi-asserted-by":"publisher","unstructured":"R. Li, D. Pan, S. Zhang, Speech enhancement algorithm based on sound source localization and scene matching for binaural digital hearing aids. J. Med. Biol. Eng. (2018). \n                    https:\/\/doi.org\/10.1007\/s40846-018-0412-z","DOI":"10.1007\/s40846-018-0412-z"},{"key":"618_CR30","volume-title":"Signal Processing for Robust Speech Recognition Motivated by Auditory Processing","author":"C Kim","year":"2010","unstructured":"C. Kim, Signal Processing for Robust Speech Recognition Motivated by Auditory ProcessingPh.D. dissertation (Carnegie Mellon University, Pittsburgh, 2010)"},{"issue":"4","key":"618_CR31","first-page":"756","volume":"48","author":"T Xiaoheng","year":"2013","unstructured":"T. Xiaoheng, Q. Jiwei, Z. Shuai, Objective evaluation method of speech quality based on auditory perceptual properties. J. Southwest Jiao Tong Univ. 48(4), 756\u2013760 (2013)","journal-title":"J. Southwest Jiao Tong Univ."},{"key":"618_CR32","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"CH Taal","year":"2011","unstructured":"C.H. Taal, R.C. Hendriks, R. Heusdens, J. Jensen, An algorithm for intelligibility prediction of time-frequency weighted noisy speech. IEEE Trans. Audio Speech Lang. Process. 19, 2125\u20132136 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"618_CR33","volume-title":"Perceptual Evaluation of Speech Quality (PESQ), an Objective Method for End-to-End Speech Quality Assessment of Narrowband Telephone Networks and Speech Codecs","author":"ITU-T Recommendation P. 862","year":"2001","unstructured":"ITU-T Recommendation P. 862, Perceptual Evaluation of Speech Quality (PESQ), an Objective Method for End-to-End Speech Quality Assessment of Narrowband Telephone Networks and Speech Codecs (International Telecommunication Union, Geneva, 2001)"}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-019-0618-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13634-019-0618-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-019-0618-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,31]],"date-time":"2020-03-31T23:13:41Z","timestamp":1585696421000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-019-0618-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,2]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["618"],"URL":"https:\/\/doi.org\/10.1186\/s13634-019-0618-4","relation":{},"ISSN":["1687-6180"],"issn-type":[{"type":"electronic","value":"1687-6180"}],"subject":[],"published":{"date-parts":[[2019,4,2]]},"assertion":[{"value":"29 September 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study does not involve human participants, human data, or human tissue.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"In the manuscript, there is no any individual person\u2019s data.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Publisher\u2019s Note"}}],"article-number":"22"}}