{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:33:12Z","timestamp":1742999592665,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030923068"},{"type":"electronic","value":"9783030923075"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-92307-5_7","type":"book-chapter","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T14:04:20Z","timestamp":1638799460000},"page":"55-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech Dereverberation Based on\u00a0Scale-Aware Mean Square Error Loss"],"prefix":"10.1007","author":[{"given":"Luya","family":"Qiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,12,2]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TNET.2013.2258036","volume":"22","author":"J Li","year":"2014","unstructured":"Li, J., Deng, L., Gong, Y., Haeb-Umbach, R.: An overview of noise-robust automatic speech recognition. IEEE\/ACM TASLP 22, 745\u2013777 (2014)","journal-title":"IEEE\/ACM TASLP"},{"key":"7_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-014-0045-2","volume":"2015","author":"Z Zhang","year":"2015","unstructured":"Zhang, Z., Wang, L., Kai, A., Yamada, T., Li, W., Iwahashi, M.: Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification. EURASIP J. Audio Speech Music Process. 2015, 1\u201313 (2015)","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"7_CR3","first-page":"1717","volume":"18","author":"T Nakatani","year":"2010","unstructured":"Nakatani, T., Yoshioka, T., Kinoshita, K., Miyoshi, M., Juang, B.-H.: Speech dereverberation based on variance-normalized delayed linear prediction. IEEE TASLP 18, 1717\u20131731 (2010)","journal-title":"IEEE TASLP"},{"issue":"9","key":"7_CR4","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1162\/NECO_a_00168","volume":"23","author":"C F\u00e9votte","year":"2011","unstructured":"F\u00e9votte, C., Idier, J.: Algorithms for nonnegative matrix factorization with the $$\\beta $$-divergence. Neural Comput. 23(9), 2421\u20132456 (2011)","journal-title":"Neural Comput."},{"issue":"6","key":"7_CR5","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1109\/TASLP.2015.2416653","volume":"23","author":"K Han","year":"2015","unstructured":"Han, K., Wang, Y., Wang, D., Woods, W.S., Merks, I., Zhang, T.: Learning spectral mapping for speech dereverberation and denoising. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(6), 982\u2013992 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Gao, T., Du, J., Dai, L.-R., Lee, C.-H.: Densely connected progressive learning for LSTM-based speech enhancement. In: Proceedings ICASSP.\u00a0IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461861"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Tang, X., Du, J., Chai, L., Wang, Y., Wang, Q., Lee, C.-H.: A LSTM-based joint progressive learning framework for simultaneous speech dereverberation and denoising. In: Proceedings APSIPA ASC. IEEE (2019)","DOI":"10.1109\/APSIPAASC47483.2019.9023160"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Kinoshita, K., et al.: The reverb challenge: a common evaluation framework for dereverberation and recognition of reverberant speech. In: Proceedings WASPAA.\u00a0IEEE (2013)","DOI":"10.1109\/WASPAA.2013.6701894"},{"key":"7_CR9","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: Proceedings ICASSP, vol. 2. IEEE (2001)","DOI":"10.1109\/ICASSP.2001.941023"},{"issue":"1","key":"7_CR10","first-page":"229","volume":"16","author":"Y Hu","year":"2007","unstructured":"Hu, Y., Loizou, P.C.: Evaluation of objective quality measures for speech enhancement. IEEE TASLP 16(1), 229\u2013238 (2007)","journal-title":"IEEE TASLP"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Takeuchi, D., Yatabe, K., Koizumi, Y., Oikawa, Y., Harada, N.: Data-driven design of perfect reconstruction filterbank for dnn-based sound source enhancement. In: Proceedings ICASSP.\u00a0IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683861"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Robinson, T., Fransen, J., Pye, D., Foote, J., Renals, S.: Wsjcamo: a british english speech corpus for large vocabulary continuous speech recognition. In: Proceedings ICASSP, vol. 1. IEEE (1995)","DOI":"10.1109\/ICASSP.1995.479278"},{"issue":"5","key":"7_CR13","first-page":"845","volume":"13","author":"R Martin","year":"2005","unstructured":"Martin, R.: Speech enhancement based on minimum mean-square error estimation and supergaussian priors. IEEE TASLP 13(5), 845\u2013856 (2005)","journal-title":"IEEE TASLP"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Erdogan, H., Hershey, J.R., Watanabe, S.,\u00a0Le\u00a0Roux, J.: Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks. In: Proceedings ICASSP.\u00a0IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"7_CR15","first-page":"1305","volume":"15","author":"Y Avargel","year":"2007","unstructured":"Avargel, Y., Cohen, I.: System identification in the short-time fourier transform domain with crossband filtering. IEEE TASLP 15, 1305\u20131319 (2007)","journal-title":"IEEE TASLP"},{"key":"7_CR16","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 \u2013 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"},{"key":"7_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-00889-5_1","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"Z Zhou","year":"2018","unstructured":"Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., Liang, J.: UNet++: a nested U-net architecture for medical image segmentation. In: Stoyanov, D., et al. (eds.) DLMIA\/ML-CDS -2018. LNCS, vol. 11045, pp. 3\u201311. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00889-5_1"},{"key":"7_CR18","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2013","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, 65\u201368 (2013)","journal-title":"IEEE Signal Process. Lett."},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Tan, K., Wang, D.: Complex spectral mapping with a convolutional recurrent network for monaural speech enhancement. In: Proceedings ICASSP.\u00a0IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Park, S.R., Lee, J.: A fully convolutional neural network for speech enhancement (2016). arXiv preprint arXiv:1609.07132","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Weninger, F., Watanabe, S., Tachioka, Y., Schuller, B.: Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition. In: Proceedings ICASSP.\u00a0IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854478"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Wang, K., Zhang, J. , Sun, S., Wang, Y., Xiang, F., Xie, L.: Investigating generative adversarial networks based speech dereverberation for robust speech recognition (2018). arXiv preprint arXiv:1803.10132","DOI":"10.21437\/Interspeech.2018-1780"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Fu, S.W., Yu, T., Lu, X., et al.: Raw waveform-based speech enhancement by fully convolutional networks. In: Proceedings APSIPA ASC.\u00a0IEEE (2017)","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Li, C., Wang, T., Xu, S., Xu, B.: Single-channel speech dereverberation via generative adversarial training (2018). arXiv preprint arXiv:1806.09325","DOI":"10.21437\/Interspeech.2018-1234"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92307-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T21:37:47Z","timestamp":1726263467000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92307-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030923068","9783030923075"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92307-5_7","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 December 2021","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":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1093","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"226","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"177","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"21% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.57","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}