{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:24:33Z","timestamp":1783103073148,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698042","type":"print"},{"value":"9789819698059","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-9805-9_2","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T05:53:45Z","timestamp":1753422825000},"page":"15-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A New Perspective on Speaker Verification: Joint Modeling with DFSMN and Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3407-6036","authenticated-orcid":false,"given":"Hongyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4307-0190","authenticated-orcid":false,"given":"Hui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Jakubec, M., Jarina, R., Lieskovska, E., Kasak, P.: Deep speaker embeddings for speaker verification: review and experimental comparison. Eng. Appl. Artif. Intell. 127, 107232","DOI":"10.1016\/j.engappai.2023.107232"},{"key":"2_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.123004","volume":"244","author":"Q Zheng","year":"2024","unstructured":"Zheng, Q., Chen, Z., Wang, Z., Liu, H., Lin, M.: MEConformer: highly representative embedding extractor for speaker verification via incorporating selective convolution into deep speaker encoder. Expert Syst. Appl. 244, 123004 (2024)","journal-title":"Expert Syst. Appl."},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Wang, Q., Lee, K. A., Liu, T.: Incorporating uncertainty from speaker embedding estimation to speaker verification. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10097019"},{"key":"2_CR4","unstructured":"Liu, T., Lee, K.A., Wang, Q., Li, H.: Golden Gemini is All You Need: Finding the Sweet"},{"key":"2_CR5","unstructured":"Spots for Speaker Verification. IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"2_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2023.103001","volume":"155","author":"Y Duan","year":"2023","unstructured":"Duan, Y., Long, Y., Liang, J.: Dual-model self-regularization and fusion for domain adaptation of robust speaker verification. Speech Commun. 155, 103001 (2023)","journal-title":"Speech Commun."},{"key":"2_CR7","unstructured":"Al-Kaltakchi, M.T., Al-Nima, R.R.O., Alfathe, M., Abdullah, M.A.: Speaker Verification"},{"key":"2_CR8","unstructured":"Using vosine distance scoring with i-vector approach. In: 2020 International Conference on Computer Science and Software Engineering (CSASE), pp. 157\u2013161. IEEE (2020)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Li, J., Han, J., Song, H.: CDMA: cross-domain distance metric adaptation for speaker verification. In ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7197\u20137201. IEEE","DOI":"10.1109\/ICASSP43922.2022.9747907"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Yu, Y.Q., Li, W.J.: Densely connected time delay neural network for speaker verification. Interspeech. 2020","DOI":"10.21437\/Interspeech.2020-1275"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Rouvier, M., Dufour, R., Bousquet, P.M.: Review of different robust X-vector extractors for speaker verification. In: 2020 28th European Signal Processing Conference (EUSIPCO). IEEE (2021)","DOI":"10.23919\/Eusipco47968.2020.9287426"},{"key":"2_CR12","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: Ecapa-tdnn: emphasized channel attention, propagation and aggregation in tdnn based speaker verification. unpublished"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2_CR14","unstructured":"Wang, H., Zheng, S., Chen, Y., Cheng, L., Chen, Q.: Cam++: a fast and efficient network for speaker verification using context-aware masking. unpublished"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Zhou, T., Zhao, Y., Wu, J.: Resnext and Res2Net structures for speaker verification (2021)","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"2_CR16","unstructured":"IEEE Spoken Language Technology Workshop (SLT). IEEE (2021)"},{"issue":"12","key":"2_CR17","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","volume":"33","author":"Z Li","year":"2021","unstructured":"Li, Z., Liu, F., Yang, W., Peng, S., Zhou, J.: A survey of convolutional neural networks: analysis applications, and prospects. IEEE Trans. Neural Netw. Learn. Syst. 33(12), 6999\u20137019 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"2","key":"2_CR18","first-page":"143","volume":"6","author":"A Mittal","year":"2021","unstructured":"Mittal, A., Dua, M.: Automatic speaker verification system using three dimensional static and contextual variation-based features with two dimensional convolutional neural network. Int. J. Swarm Intell. 6(2), 143\u2013153 (2021)","journal-title":"Int. J. Swarm Intell."},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., Tian, Y., Lee, T.: Convolution-based channel-frequency attention for text-independent speaker verification. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095415"},{"key":"2_CR20","unstructured":"Zhang, Y., et al..: Mfa-conformer: multi-scale feature aggregation conformer for automatic speaker verification. unpublished"},{"key":"2_CR21","unstructured":"Dosovitskiy, A., et al.: An Image Is Worth 16x16 words: transformers for image recognition at scale. unpublished"},{"key":"2_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. (2017)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, S., Lei, M., Yan, Z., Dai, L.: Deep-FSMN for large vocabulary continuous speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461404"},{"key":"2_CR24","unstructured":"Gao, Z., Zhang, S., Lei, M., Mcloughlin, I.: San-m: memory equipped self-attention for end-to-end speech recognition. unpublished"},{"key":"2_CR25","unstructured":"Okabe, K., Koshinaka, T., Shinoda, K.: attentive statistics pooling for deep speaker embedding. unpublished"},{"key":"2_CR26","unstructured":"Ross, T.Y., Doll\u00e1r, G.K.H.P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (2017)"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Sign. Process. Lett. 25(7), 926\u2013 930 (2018). IEEE","DOI":"10.1109\/LSP.2018.2822810"},{"key":"2_CR29","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: Voxceleb: a large-scale speaker identification dataset. unpublished"},{"key":"2_CR30","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). IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"2_CR31","unstructured":"Povey, D., et al.: The kaldi speech recognition toolkit. IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Sign. Process. Soc. (2011)"},{"key":"2_CR32","unstructured":"Chung, J.S., et al.: In: Defence of Metric Learning for Speaker Recognition. unpublished"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Koonce, B.: ResNet 34. convolutional neural networks with swift for tensorflow: image recognition and dataset categorization, 51\u201361 (2021)","DOI":"10.1007\/978-1-4842-6168-2_5"},{"key":"2_CR34","unstructured":"Jung, J.W., Kim, S.B., Shim, H.J., Kim, J.H., Yu, H.J.: Improved rawnet with feature map scaling for text-independent speaker verification using raw waveforms. unpublished"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9805-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:02:23Z","timestamp":1783101743000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9805-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698042","9789819698059"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9805-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}