{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:37:07Z","timestamp":1743043027786,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031483080"},{"type":"electronic","value":"9783031483097"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-48309-7_22","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"258-270","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ATT:Adversarial Trained Transformer for\u00a0Speech Enhancement"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1210-904X","authenticated-orcid":false,"given":"Aniket","family":"Aitawade","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3468-623X","authenticated-orcid":false,"given":"Puja","family":"Bharati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3051-247X","authenticated-orcid":false,"given":"Sabyasachi","family":"Chandra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G. Satya","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2170-4450","authenticated-orcid":false,"given":"Debolina","family":"Pramanik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4321-6936","authenticated-orcid":false,"given":"Parth Sanjay","family":"Khadse","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4088-3173","authenticated-orcid":false,"given":"Shyamal Kumar","family":"Das Mandal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"issue":"1","key":"22_CR1","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TASL.2007.911054","volume":"16","author":"Y Hu","year":"2007","unstructured":"Hu, Y., Loizou, P.C.: Evaluation of objective quality measures for speech enhancement. IEEE Trans. Audio Speech Lang. Process. 16(1), 229\u2013238 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"22_CR3","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. CRC Press, Boca Raton (2013)"},{"issue":"7","key":"22_CR4","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/TASLP.2019.2913512","volume":"27","author":"A Pandey","year":"2019","unstructured":"Pandey, A., Wang, D.: A new framework for CNN-based speech enhancement in the time domain. IEEE\/ACM Trans. Audio, Speech Lang. Process. 27(7), 1179\u20131188 (2019)","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Process."},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Pandey, A., Wang, D.: TCNN: temporal convolutional neural network for real-time speech enhancement in the time domain. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6875\u20136879. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Park, S.R., Lee, J.: A fully convolutional neural network for speech enhancement. arXiv preprint arXiv:1609.07132 (2016)","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Pascual, S., Bonafonte, A., Serra, J.: SEGAN: speech enhancement generative adversarial network. arXiv preprint arXiv:1703.09452 (2017)","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"22_CR9","unstructured":"Rec, I.: P. 862.2: Wideband extension to recommendation p. 862 for the assessment of wideband telephone networks and speech codecs. International Telecommunication Union, CH-Geneva (2005)"},{"key":"22_CR10","doi-asserted-by":"publisher","unstructured":"Shahriyar, S.A., Akhand, M.A.H., Siddique, N., Shimamura, T.: Speech enhancement using convolutional denoising autoencoder. In: 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE), pp. 1\u20135 (2019). https:\/\/doi.org\/10.1109\/ECACE.2019.8679106","DOI":"10.1109\/ECACE.2019.8679106"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Sun, L., Du, J., Dai, L.R., Lee, C.H.: Multiple-target deep learning for LSTM-RNN based speech enhancement. In: 2017 Hands-free Speech Communications and Microphone Arrays (HSCMA), pp. 136\u2013140. IEEE (2017)","DOI":"10.1109\/HSCMA.2017.7895577"},{"issue":"7","key":"22_CR12","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"CH Taal","year":"2011","unstructured":"Taal, C.H., Hendriks, R.C., Heusdens, R., Jensen, J.: An algorithm for intelligibility prediction of time-frequency weighted noisy speech. IEEE Trans. Audio Speech Lang. Process. 19(7), 2125\u20132136 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Tawara, N., Kobayashi, T., Ogawa, T.: Multi-channel speech enhancement using time-domain convolutional denoising autoencoder. In: INTERSPEECH, pp. 86\u201390 (2019)","DOI":"10.21437\/Interspeech.2019-3197"},{"key":"22_CR14","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"22_CR15","unstructured":"Xu, Y., Du, J., Huang, Z., Dai, L.R., Lee, C.H.: Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement. arXiv preprint arXiv:1703.07172 (2017)"},{"issue":"3","key":"22_CR16","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1121\/1.1852873","volume":"117","author":"LP Yang","year":"2005","unstructured":"Yang, L.P., Fu, Q.J.: Spectral subtraction-based speech enhancement for cochlear implant patients in background noise. J. Acoust. Soc. Am. 117(3), 1001\u20131004 (2005)","journal-title":"J. Acoust. Soc. Am."},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Yu, D., Deng, L., Droppo, J., Wu, J., Gong, Y., Acero, A.: A minimum-mean-square-error noise reduction algorithm on Mel-frequency cepstra for robust speech recognition. In: 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4041\u20134044. IEEE (2008)","DOI":"10.1109\/ICASSP.2008.4518541"},{"key":"22_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12559-020-09817-2","volume":"14","author":"W Yu","year":"2022","unstructured":"Yu, W., Zhou, J., Wang, H., Tao, L.: Setransformer: speech enhancement transformer. Cogn. Comput. 14, 1\u20137 (2022). https:\/\/doi.org\/10.1007\/s12559-020-09817-2","journal-title":"Cogn. Comput."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48309-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T14:48:59Z","timestamp":1730558939000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48309-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483080","9783031483097"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48309-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dharwad","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iitdh.ac.in\/specom-2023\/","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":"174","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":"94","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":"0","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":"54% - 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":"3","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":"4","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)"}}]}}