{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:35:49Z","timestamp":1763202949246,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031780134"},{"type":"electronic","value":"9783031780141"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-78014-1_12","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:25:19Z","timestamp":1732191919000},"page":"157-170","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["On the\u00a0Influence of\u00a0CNN-Based Feature Learning Modules in\u00a0Neural Speaker Verification Framework"],"prefix":"10.1007","author":[{"given":"Jahangir","family":"Alam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Md Shahidul","family":"Alam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","unstructured":"Alam, J.: On the use of cross- and self-module attentive statistics pooling techniques for text-independent speaker verification. In: IEEE International Joint Conference on Biometrics (IJCB), pp.\u00a01\u20139 (2023). https:\/\/doi.org\/10.1109\/IJCB57857.2023.10448902","DOI":"10.1109\/IJCB57857.2023.10448902"},{"key":"12_CR2","doi-asserted-by":"publisher","unstructured":"Alam, J., Fathan, A., Kang, W.H.: Text-independent speaker verification employing CNN-LSTM-TDNN hybrid networks. In: Proceedings of the of SPECOM, vol. 12997, pp. 1\u201313 (2021). https:\/\/doi.org\/10.1007\/978-3-030-87802-3_1","DOI":"10.1007\/978-3-030-87802-3_1"},{"key":"12_CR3","doi-asserted-by":"publisher","unstructured":"Alam, J., Kang, W.H., Fathan, A.: Hybrid neural network with cross- and self-module attention pooling for text-independent speaker verification. In: IEEE ICASSP, pp.\u00a01\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10096040","DOI":"10.1109\/ICASSP49357.2023.10096040"},{"key":"12_CR4","unstructured":"Cai, Y., Li, L., Wang, D., Abel, A.: Deep speaker vector normalization with maximum Gaussianality training (2020)"},{"key":"12_CR5","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"},{"key":"12_CR6","doi-asserted-by":"publisher","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: Ecapa-tdnn: emphasized channel attention, propagation and aggregation in TDNN based speaker verification. In: Interspeech. ISCA (2020). https:\/\/doi.org\/10.21437\/interspeech.2020-2650","DOI":"10.21437\/interspeech.2020-2650"},{"key":"12_CR7","doi-asserted-by":"publisher","unstructured":"Garcia-Romero, D., McCree, A., Snyder, D., Sell, G.: Jhu-hltcoe system for the voxsrc speaker recognition challenge. In: IEEE ICASSP, pp. 7559\u20137563 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053209","DOI":"10.1109\/ICASSP40776.2020.9053209"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Gusev, A., et\u00a0al.: Deep speaker embeddings for far-field speaker recognition on short utterances (2020)","DOI":"10.21437\/Odyssey.2020-26"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Huang, C.L.: Speaker characterization using TDNN, TDNN-LSTM, TDNN-LSTM-attention based speaker embeddings for NIST SRE 2019. In: Proceedings of Odyssey, pp. 423\u2013427 (2020)","DOI":"10.21437\/Odyssey.2020-60"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Kang, W.H., Alam, J., Fathan, A.: Hybrid network with multi-level global-local statistics pooling for robust text-independent speaker recognition. In: Proceedings of ASRU, pp. 1116\u20131123 (2021)","DOI":"10.1109\/ASRU51503.2021.9687877"},{"key":"12_CR11","doi-asserted-by":"publisher","unstructured":"Kang, W.H., Alam, J., Fathan, A.: Hybrid network with multi-level global-local statistics pooling for robust text-independent speaker recognition. In: Proceedings of ASRU, pp. 1116\u20131123 (2021). https:\/\/doi.org\/10.1109\/ASRU51503.2021.9687877","DOI":"10.1109\/ASRU51503.2021.9687877"},{"key":"12_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) Proceedings of ICLR (2015). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"12_CR13","doi-asserted-by":"publisher","unstructured":"Liu, T., Das, R.K., Aik\u00a0Lee, K., Li, H.: MFA: TDNN with multi-scale frequency-channel attention for text-independent speaker verification with short utterances. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7517\u20137521 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747021","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"12_CR14","unstructured":"Mun, S.H., Weon Jung, J., Kim, N.S.: Selective kernel attention for robust speaker verification. arXiv preprint arXiv:2204.01005 (2022)"},{"key":"12_CR15","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":"12_CR16","doi-asserted-by":"crossref","unstructured":"Novoselov, S., Shulipa, A., Kremnev, I., Kozlov, A., Shchemelinin, V.: On deep speaker embeddings for text-independent speaker recognition. arXiv preprint arXiv:1804.10080 (2018)","DOI":"10.21437\/Odyssey.2018-53"},{"key":"12_CR17","doi-asserted-by":"publisher","unstructured":"Peng, Z., He, X., Ding, K., Lee, T., Wan, G.: Unifying cosine and PLDA back-ends for speaker verification. In: Proceedings of the Interspeech, pp. 336\u2013340 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10021","DOI":"10.21437\/Interspeech.2022-10021"},{"key":"12_CR18","doi-asserted-by":"publisher","unstructured":"Sainath, T.N., Vinyals, O., Senior, A., Sak, H.: Convolutional, long short-term memory, fully connected deep neural networks. In: Proceedings of IEEE ICASSP, pp. 4580\u20134584 (2015). https:\/\/doi.org\/10.1109\/ICASSP.2015.7178838","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"12_CR19","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: Proceedings of ICASSP, pp. 5329\u20135333. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"12_CR20","doi-asserted-by":"publisher","unstructured":"Snyder, D., et\u00a0al.: The JHU speaker recognition system for the VOiCES 2019 challenge. In: Proceedings of the Interspeech 2019, pp. 2468\u20132472 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-2979","DOI":"10.21437\/Interspeech.2019-2979"},{"key":"12_CR21","doi-asserted-by":"publisher","unstructured":"Thienpondt, J., Desplanques, B., Demuynck, K.: Integrating frequency translational invariance in TDNNS and frequency positional information in 2d resnets to enhance speaker verification. In: Interspeech 2021. ISCA (2021). https:\/\/doi.org\/10.21437\/interspeech.2021-1570","DOI":"10.21437\/interspeech.2021-1570"},{"key":"12_CR22","doi-asserted-by":"publisher","unstructured":"Variani, E., Lei, X., McDermott, E., Moreno, I.L., Gonzalez-Dominguez, J.: Deep neural networks for small footprint text-dependent speaker verification. In: Proceedings of ICASSP, pp. 4052\u20134056 (2014). https:\/\/doi.org\/10.1109\/ICASSP.2014.6854363","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Villalba, J., et\u00a0al.: State-of-the-art speaker recognition for telephone and video speech: the JHU-MIT submission for NIST SRE18. In: Proceedings of the Interspeech 2019, pp. 1488\u20131492 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-2713","DOI":"10.21437\/Interspeech.2019-2713"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Q., Lee, K.A., Liu, T.: Scoring of Large-Margin Embeddings for Speaker Verification: Cosine or PLDA? pp. 600\u2013603 (2022). https:\/\/www.isca-archive.org\/interspeech_2022\/wang22r_interspeech.pdf","DOI":"10.21437\/Interspeech.2022-10055"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Wang, S., Rohdin, J., Plchot, O., Burget, L., Yu, K., \u010cernock\u00fd, J.: Investigation of specaugment for deep speaker embedding learning. In: Proceedings of ICASSP, pp. 7139\u20137143 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053481"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Yu, Y.Q., Li, W.J.: Densely connected time delay neural network for speaker verification. In: Interspeech (2020). https:\/\/api.semanticscholar.org\/CorpusID:226201807","DOI":"10.21437\/Interspeech.2020-1275"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Aret: aggregated residual extended time-delay neural networks for speaker verification. In: Proceedings of ISCA Interspeech, pp. 946\u2013950 (2020)","DOI":"10.21437\/Interspeech.2020-1626"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78014-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T13:05:46Z","timestamp":1732194346000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78014-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031780134","9783031780141"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78014-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","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":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","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":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}