{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:54:04Z","timestamp":1726062844362},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030367077"},{"type":"electronic","value":"9783030367084"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-36708-4_8","type":"book-chapter","created":{"date-parts":[[2019,12,12]],"date-time":"2019-12-12T15:24:22Z","timestamp":1576164262000},"page":"86-97","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Learning an Adversarial Network for Speech Enhancement Under Extremely Low Signal-to-Noise Ratio Condition"],"prefix":"10.1007","author":[{"given":"Xiangdong","family":"Su","sequence":"first","affiliation":[]},{"given":"Xiang","family":"Hao","sequence":"additional","affiliation":[]},{"given":"Zhiyu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yun","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Huali","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Tongyang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[]},{"family":"Feilong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,9]]},"reference":[{"key":"8_CR1","unstructured":"Denton, E.L., Chintala, S., Szlam, A., Fergus, R.: Deep generative image models using a Laplacian pyramid of adversarial networks. In: NIPS (2015)"},{"issue":"10","key":"8_CR2","doi-asserted-by":"publisher","first-page":"1526","DOI":"10.1109\/5.168664","volume":"80","author":"Y Ephraim","year":"1992","unstructured":"Ephraim, Y.: Statistical-model-based speech enhancement systems. Proc. IEEE 80(10), 1526\u20131555 (1992). https:\/\/doi.org\/10.1109\/5.168664","journal-title":"Proc. IEEE"},{"key":"8_CR3","doi-asserted-by":"publisher","unstructured":"Erdogan, H., Hershey, J.R., Watanabe, S., Le Roux, J.: Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 708\u2013712, April 2015. https:\/\/doi.org\/10.1109\/ICASSP.2015.7178061","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"8_CR4","unstructured":"Gauthier, J.: Conditional generative adversarial nets for convolutional face generation (2014)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Ghael, S., Sayeed, A.M., Baraniuk, R.G.: Improved wavelet denoising via empirical Wiener filtering. In: SPIE Technical Conference on Wavelet Applications in Signal Processing (1997)","DOI":"10.1117\/12.292799"},{"key":"8_CR6","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: International Conference on Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"8_CR7","unstructured":"Granovetter, R.P., Sinclair, M.J., Zhang, Z., Liu, Z.: Method and apparatus for multi-sensory speech enhancement on a mobile device. US Patent 7,283,850, 16 October 2007"},{"key":"8_CR8","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37, ICML 2015, pp. 448\u2013456. JMLR.org (2015)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"8_CR10","unstructured":"Karacan, L., Akata, Z., Erdem, A., Erdem, E.: Learning to generate images of outdoor scenes from attributes and semantic layouts. arXiv preprint arXiv:1612.00215 (2016)"},{"key":"8_CR11","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, December 2014"},{"key":"8_CR12","doi-asserted-by":"publisher","DOI":"10.1201\/b14529","volume-title":"Speech Enhancement: Theory and Practice","author":"PC Loizou","year":"2013","unstructured":"Loizou, P.C.: Speech Enhancement: Theory and Practice, 2nd edn. CRC Press Inc., Boca Raton (2013)","edition":"2"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Lu, X., Tsao, Y., Matsuda, S., Hori, C.: Speech enhancement based on deep denoising autoencoder (2013)","DOI":"10.21437\/Interspeech.2013-130"},{"key":"8_CR14","doi-asserted-by":"publisher","unstructured":"Michelsanti, D., Tan, Z.H.: Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification. In: Proceedings of the Interspeech 2017, pp. 2008\u20132012. ISCA (2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-1620","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"8_CR15","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv:1411.1784 , November 2014"},{"key":"8_CR16","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Park, S.R., Lee, J.: A fully convolutional neural network for speech enhancement. In: INTERSPEECH (2017)","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"8_CR18","unstructured":"Parveen, S., Green, P.: Speech enhancement with missing data techniques using recurrent neural networks. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, p. I-733-6 (2004)"},{"key":"8_CR19","doi-asserted-by":"publisher","unstructured":"Pascual, S., Bonafonte, A., Serr\u00e0, J.: SEGAN: speech enhancement generative adversarial network. In: Proceedings of the Interspeech 2017, pp. 3642\u20133646 (2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-1428","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"8_CR20","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. arXiv preprint arXiv:1605.05396 (2016)"},{"key":"8_CR21","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: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 749\u2013752 (2001)"},{"key":"8_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2014 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"issue":"3","key":"8_CR23","doi-asserted-by":"publisher","first-page":"1827","DOI":"10.1121\/1.420107","volume":"102","author":"GH Saunders","year":"1997","unstructured":"Saunders, G.H., Kates, J.M.: Speech intelligibility enhancement using hearing-aid array processing. J. Acoust. Soc. Am. 102(3), 1827\u20131837 (1997)","journal-title":"J. Acoust. Soc. Am."},{"key":"8_CR24","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: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4214\u20134217. IEEE (2010)","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"8_CR25","doi-asserted-by":"publisher","DOI":"10.1002\/9780470740156","volume-title":"Advanced Digital Signal Processing and Noise Reduction","author":"SV Vaseghi","year":"2008","unstructured":"Vaseghi, S.V.: Advanced Digital Signal Processing and Noise Reduction. Wiley, Hoboken (2008)"},{"key":"8_CR26","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860","volume-title":"Audio Source Separation and Speech Enhancement","author":"E Vincent","year":"2018","unstructured":"Vincent, E., Virtanen, T., Gannot, S.: Audio Source Separation and Speech Enhancement. Wiley, Hoboken (2018)"},{"issue":"4","key":"8_CR27","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TASSP.1982.1163920","volume":"30","author":"D Wang","year":"1982","unstructured":"Wang, D., Lim, J.: The unimportance of phase in speech enhancement. IEEE Trans. Acoust. Speech Signal Process. 30(4), 679\u2013681 (1982). https:\/\/doi.org\/10.1109\/TASSP.1982.1163920","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"10","key":"8_CR28","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159","volume":"26","author":"D Wang","year":"2018","unstructured":"Wang, D., Chen, J.: Supervised speech separation based on deep learning: an overview. IEEE\/ACM Trans. Audio Speech Lang. Process. 26(10), 1702\u20131726 (2018)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"8_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","volume-title":"Latent Variable Analysis and Signal Separation","author":"F Weninger","year":"2015","unstructured":"Weninger, F., et al.: Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR. In: Vincent, E., Yeredor, A., Koldovsk\u00fd, Z., Tichavsk\u00fd, P. (eds.) LVA\/ICA 2015. LNCS, vol. 9237, pp. 91\u201399. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-22482-4_11"},{"key":"8_CR30","unstructured":"Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)"},{"issue":"1","key":"8_CR31","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., Lee, C.: A regression approach to speech enhancement based on deep neural networks. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(1), 7\u201319 (2015). https:\/\/doi.org\/10.1109\/TASLP.2014.2364452","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"8_CR32","unstructured":"Wang, Y., Brookes, M.: A subspace method for speech enhancement in the modulation domain. In: 21st European Signal Processing Conference (EUSIPCO 2013), pp. 1\u20135, September 2013"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36708-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T09:48:34Z","timestamp":1665222514000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-36708-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030367077","9783030367084"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36708-4_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ajiips.com.au\/iconip2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}