{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:30:11Z","timestamp":1772645411378,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819985487","type":"print"},{"value":"9789819985494","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8549-4_38","type":"book-chapter","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:01:32Z","timestamp":1703440892000},"page":"457-468","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["DFR-ECAPA: Diffusion Feature Refinement for\u00a0Speaker Verification Based on\u00a0ECAPA-TDNN"],"prefix":"10.1007","author":[{"given":"Ya","family":"Gao","sequence":"first","affiliation":[]},{"given":"Wei","family":"Song","sequence":"additional","affiliation":[]},{"given":"Xiaobing","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Xiangchun","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"38_CR1","unstructured":"Baranchuk, D., Rubachev, I., Voynov, A., Khrulkov, V., Babenko, A.: Label-efficient semantic segmentation with diffusion models. arXiv preprint arXiv:2112.03126 (2021)"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: Voxceleb2: deep speaker recognition. arXiv preprint arXiv:1806.05622 (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"issue":"4","key":"38_CR3","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Deja, K., Trzcinski, T., Tomczak, J.M.: Learning data representations with joint diffusion models. arXiv preprint arXiv:2301.13622 (2023)","DOI":"10.1007\/978-3-031-43415-0_32"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification. arXiv preprint arXiv:2005.07143 (2020)","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Dowerah, S., Serizel, R., Jouvet, D., Mohammadamini, M., Matrouf, D.: Joint optimization of diffusion probabilistic-based multichannel speech enhancement with far-field speaker verification. In: 2022 IEEE Spoken Language Technology Workshop (SLT), pp. 428\u2013435. IEEE (2023)","DOI":"10.1109\/SLT54892.2023.10022350"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Fan, Y., et al.: Cn-celeb: a challenging Chinese speaker recognition dataset. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7604\u20137608. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"38_CR8","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"38_CR9","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv preprint arXiv:2204.03458 (2022)"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Huang, R., et al.: FastDiff: a fast conditional diffusion model for high-quality speech synthesis. arXiv preprint arXiv:2204.09934 (2022)","DOI":"10.24963\/ijcai.2022\/577"},{"key":"38_CR11","doi-asserted-by":"publisher","first-page":"30743","DOI":"10.1007\/s11042-020-10165-4","volume":"80","author":"P Li","year":"2021","unstructured":"Li, P., Tang, H., Yu, J., Song, W.: LSTM and multiple CNNs based event image classification. Multimed. Tools Appl. 80, 30743\u201330760 (2021)","journal-title":"Multimed. Tools Appl."},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Liu, T., Das, R.K., Lee, K.A., Li, H.: MFA: TDNN with multi-scale frequency-channel attention for text-independent speaker verification with short utterances. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7517\u20137521. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Mun, S.H., Jung, J.w., Han, M.H., Kim, N.S.: Frequency and multi-scale selective kernel attention for speaker verification. In: 2022 IEEE Spoken Language Technology Workshop (SLT), pp. 548\u2013554. IEEE (2023)","DOI":"10.1109\/SLT54892.2023.10023305"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612 (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"38_CR15","unstructured":"Popov, V., Vovk, I., Gogoryan, V., Sadekova, T., Kudinov, M., Wei, J.: Diffusion-based voice conversion with fast maximum likelihood sampling scheme (2022)"},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Sawata, R., et al.: Diffiner: A versatile diffusion-based generative refiner for speech enhancement (2023)","DOI":"10.21437\/Interspeech.2023-1547"},{"key":"38_CR18","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-vectors: robust DNN embeddings for speaker recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329\u20135333. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Thienpondt, J., Desplanques, B., Demuynck, K.: Integrating frequency translational invariance in TDNNs and frequency positional information in 2d Resnets to enhance speaker verification. arXiv preprint arXiv:2104.02370 (2021)","DOI":"10.21437\/Interspeech.2021-1570"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Variani, E., Lei, X., McDermott, E., Moreno, I.L., Gonzalez-Dominguez, J.: Deep neural networks for small footprint text-dependent speaker verification. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4052\u20134056. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8798\u20138807 (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"38_CR22","unstructured":"Zeinali, H., Wang, S., Silnova, A., Mat\u011bjka, P., Plchot, O.: But system description to Voxceleb speaker recognition challenge 2019. arXiv preprint arXiv:1910.12592 (2019)"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Li, Z., Wang, W., Zhang, P.: PCF: ECAPA-TDNN with progressive channel fusion for speaker verification. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095051"},{"key":"38_CR24","unstructured":"Zhu, Z.,et al.: Exploring discrete diffusion models for image captioning. arXiv preprint arXiv:2211.11694 (2022)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8549-4_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:12:07Z","timestamp":1703441527000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8549-4_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"ISBN":["9789819985487","9789819985494"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8549-4_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"25 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}