{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T04:11:42Z","timestamp":1748578302118,"version":"3.41.0"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319224817"},{"type":"electronic","value":"9783319224824"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-22482-4_9","type":"book-chapter","created":{"date-parts":[[2015,8,14]],"date-time":"2015-08-14T07:06:02Z","timestamp":1439535962000},"page":"75-82","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Improving Deep Neural Network Based Speech Enhancement in Low SNR Environments"],"prefix":"10.1007","author":[{"given":"Tian","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Rong","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,8,15]]},"reference":[{"issue":"2","key":"9_CR1","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"S Boll","year":"1979","unstructured":"Boll, S.: 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":"2","key":"9_CR2","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1109\/TASSP.1985.1164550","volume":"33","author":"Y Ephraim","year":"1985","unstructured":"Ephraim, Y., Malah, D.: Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Trans. Acoust. Speech Signal Process. 33(2), 443\u2013445 (1985)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"5","key":"9_CR3","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1109\/TSA.2003.811544","volume":"11","author":"I Cohen","year":"2003","unstructured":"Cohen, I.: Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging. IEEE Trans. Speech Audio Process. 11(5), 466\u2013475 (2003)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"10","key":"9_CR4","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1109\/TASL.2013.2270369","volume":"21","author":"N Mohammadiha","year":"2013","unstructured":"Mohammadiha, N., Smaragdis, P., Leijon, A.: Supervised and unsupervised speech enhancement using nonnegative matrix factorization. IEEE Trans. Audio Speech Lang. Process. 21(10), 2140\u20132151 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"7","key":"9_CR5","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1109\/TASL.2013.2250961","volume":"21","author":"YX Wang","year":"2013","unstructured":"Wang, Y.X., Wang, D.L.: 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":"9_CR6","doi-asserted-by":"crossref","unstructured":"Narayanan, A., Wang, D.L.: Ideal ratio mask estimation using deep neural networks for robust speech recognition. In: ICASSP, pp. 7092\u20137096 (2013)","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Du, J., Huo, Q.: A speech enhancement approach using piecewise linear approximation of an explicit model of environmental distortions. In: INTERSPEECH, pp. 569\u2013572 (2008)","DOI":"10.21437\/Interspeech.2008-168"},{"issue":"1","key":"9_CR8","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2014","unstructured":"Xu, Y., Du, J., Dai, L.-R., Lee, C.-H.: 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."},{"issue":"1","key":"9_CR9","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","volume":"23","author":"Y Xu","year":"2015","unstructured":"Xu, Y., Du, J., Dai, L.-R., Lee, C.-H.: A regression approach to speech enhancement based on deep neural networks. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(1), 7\u201319 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Tu, Y.-H., Du, J., Xu, Y., Dai, L.-R., Lee, C.-H.: Speech separation based on improved deep neural networks with dual outputs of speech features for both target and interfering speakers. In: ISCSLP, pp. 250\u2013254 (2014)","DOI":"10.1109\/ISCSLP.2014.6936615"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Du, J., Wang, Q., Gao, T., Xu, Y., Dai, L.-R., Lee, C.-H.: Robust speech recognition with speech enhanced deep neural networks. In: INTERSPEECH, pp. 616\u2013620 (2014)","DOI":"10.21437\/Interspeech.2014-148"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Gao, T., Du, J., Dai, L.-R., Lee, C.-H.: Joint training of front-end and back-end deep neural networks for robust speech recognition. In: ICASSP (2015, accepted)","DOI":"10.1109\/ICASSP.2015.7178797"},{"issue":"3","key":"9_CR13","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.J.: 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 Commun. 12(3), 247\u2013251 (1993)","journal-title":"Speech Commun."},{"key":"9_CR14","unstructured":"Sohn, J., Sung, W.: A voice activity detector employing soft decision based noise spectrum adaptation. In: ICASSP, pp. 365\u2013368 (1998)"},{"issue":"1","key":"9_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/97.736233","volume":"6","author":"J Sohn","year":"1999","unstructured":"Sohn, J., Kim, N.S., Sung, W.: A statistical model-based voice activity detection. IEEE Signal Process. Lett. 6(1), 1\u20133 (1999)","journal-title":"IEEE Signal Process. Lett."},{"issue":"4","key":"9_CR16","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1109\/TASL.2012.2229986","volume":"21","author":"X-L Zhang","year":"2013","unstructured":"Zhang, X.-L., Wu, J.: Deep belief networks based voice activity detection. IEEE Trans. Audio Speech Lang. Process. 21(4), 697\u2013710 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, X.-L., Wang, D.L.: Boosted deep neural networks and multi-resolution cochleagram features for voice activity detection. In: INTERSPEECH, pp. 1534\u20131538 (2014)","DOI":"10.21437\/Interspeech.2014-367"},{"issue":"7","key":"9_CR18","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527\u20131554 (2006)","journal-title":"Neural Comput."},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Xu, Y., Du, J., Dai, L.-R., Lee, C.-H.: Dynamic noise aware training for speech enhancement based on deep neural networks. In: INTERSPEECH, pp. 2670\u20132674 (2014)","DOI":"10.21437\/Interspeech.2014-571"},{"key":"9_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/978-3-642-35289-8_32","volume-title":"Neural Networks: Tricks of the Trade","author":"GE Hinton","year":"2012","unstructured":"Hinton, G.E.: A practical guide to training restricted Boltzmann machines. In: Montavon, G., Orr, G.B., M\u00fcller, K.-R. (eds.) NN: Tricks of the Trade, 2nd edn. LNCS, vol. 7700, pp. 599\u2013619. Springer, Heidelberg (2012)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Taal, C.H., Hendriks, R.C., Heusdens, R., Jensen, J.: A short-time objective intelligibility measure for time-frequency weighted noisy speech. In: ICASSP, pp. 4214\u20134217 (2010)","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Rix, A.W., Beerends, J.G., Hollier, M.P., Hekstra, A.P.: Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In: ICASSP, pp. 749\u2013752 (2001)","DOI":"10.1109\/ICASSP.2001.941023"}],"container-title":["Lecture Notes in Computer Science","Latent Variable Analysis and Signal Separation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-22482-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:19:49Z","timestamp":1748564389000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-22482-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319224817","9783319224824"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-22482-4_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"15 August 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}