{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:39:10Z","timestamp":1740181150659,"version":"3.37.3"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972324","61972324","61972324","61972324","61972324"],"award-info":[{"award-number":["61972324","61972324","61972324","61972324","61972324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Membr Comput"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s41965-024-00135-2","type":"journal-article","created":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T09:01:32Z","timestamp":1710147692000},"page":"42-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Speaker recognition with global information modelling of raw waveforms"],"prefix":"10.1007","volume":"6","author":[{"given":"Yujiao","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianping","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zulin","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gexiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haina","family":"Rong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,11]]},"reference":[{"key":"135_CR1","doi-asserted-by":"publisher","first-page":"79236","DOI":"10.1109\/ACCESS.2021.3084299","volume":"9","author":"M Kabi","year":"2021","unstructured":"Kabi, M., Mridha, M. F., Shin, J., Jahan, I., & Ohi, A. Q. (2021). A survey of speaker recognition: Fundamental theories, recognition methods and opportunities. IEEE Access., 9, 79236\u201379263.","journal-title":"IEEE Access."},{"doi-asserted-by":"crossref","unstructured":"Fechner, G.T. (1948). Elements of psychophysics. IEEE Access. 1860.","key":"135_CR2","DOI":"10.1037\/11304-026"},{"doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D. & Khudanpur, S. (2018). X-vectors: Robust dnn embeddings for speaker recognition. In 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP)., 5329\u20135333.","key":"135_CR3","DOI":"10.1109\/ICASSP.2018.8461375"},{"doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J. & Demuynck, K. (2020). Ecapa-tdnn: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification. arXiv., 2005\u201307143.","key":"135_CR4","DOI":"10.21437\/Interspeech.2020-2650"},{"unstructured":"Chung, J.S., Nagrani, A. & Zisserman, A. (2020). Voxceleb2: Deep speaker recognition. arXiv., 2005\u201307143.","key":"135_CR5"},{"key":"135_CR6","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1109\/TASLP.2020.2980991","volume":"28","author":"W Cai","year":"2020","unstructured":"Cai, W., Chen, J., Zhang, J., & Li, M. (2020). On-the-fly data loader and utterance-level aggregation for speaker and language recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing., 28, 1038\u20131051.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing."},{"issue":"4","key":"135_CR7","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. (2010). Front-end factor analysis for speaker verification. IEEE Transactions on Audio, Speech and Language Processing, 19(4), 788\u2013798.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"135_CR8","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., & Auli, M. (2020). wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems, 33, 12449\u201312460.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"crossref","unstructured":"Sainath, T., Weiss, R.J., Wilson, K., Senior, A.W. & Vinyals, O. (2015). Learning the speech front-end with raw waveform cldnns. Advances in neural information processing systems.","key":"135_CR9","DOI":"10.21437\/Interspeech.2015-1"},{"doi-asserted-by":"crossref","unstructured":"Ravanelli, M. & Bengio, Y. (2018). Speaker recognition from raw waveform with sincnet. In 2018 IEEE spoken language technology workshop (SLT)., 1021\u20131028.","key":"135_CR10","DOI":"10.1109\/SLT.2018.8639585"},{"doi-asserted-by":"crossref","unstructured":"Oglic, D., Cvetkovic, Z., Bell, P. & Renals, S. (2020). A deep 2d convolutional network for waveform-based speech recognition. Interspeech., 1654\u20131658.","key":"135_CR11","DOI":"10.21437\/Interspeech.2020-1870"},{"doi-asserted-by":"crossref","unstructured":"Pariente, M., Cornell, S., Deleforge, A. & Vincent, E. (2020). Filterbank design for end-to-end speech separation. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 6364\u20136368.","key":"135_CR12","DOI":"10.1109\/ICASSP40776.2020.9053038"},{"doi-asserted-by":"crossref","unstructured":"Jung, J.W., Heo, H.S., Yang, I.H., Shim, H.J. & Yu, H.J. (2018). A complete end-to-end speaker verification system using deep neural networks: From raw signals to verification result. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 5349\u20135353.","key":"135_CR13","DOI":"10.1109\/ICASSP.2018.8462575"},{"doi-asserted-by":"crossref","unstructured":"Muckenhirn, H., Doss, M.M. & Marcell, S. (2018). Towards directly modeling raw speech signal for speaker verification using cnns. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 4884\u20134888.","key":"135_CR14","DOI":"10.1109\/ICASSP.2018.8462165"},{"doi-asserted-by":"crossref","unstructured":"Zhu, G., Jiang, F. & Duan, Z. (2020). Y-vector: Multiscale waveform encoder for speaker embedding. arXiv, 2010\u201312951","key":"135_CR15","DOI":"10.21437\/Interspeech.2021-1707"},{"doi-asserted-by":"crossref","unstructured":"Jung, J.W., Kim, Y.J., Heo, H.S., Lee, B.J., Kwon, Y. & Chung, J.S. (2022). Pushing the limits of raw waveform speaker recognition. arXiv, 2203\u201308488.","key":"135_CR16","DOI":"10.21437\/Interspeech.2022-126"},{"unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N. & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.","key":"135_CR17"},{"issue":"12","key":"135_CR18","doi-asserted-by":"publisher","first-page":"11106","DOI":"10.1609\/aaai.v35i12.17325","volume":"35","author":"H Zhou","year":"2021","unstructured":"Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., & Zhang, W. (2021). Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI conference on artificial intelligence, 35(12), 11106\u201311115.","journal-title":"In Proceedings of the AAAI conference on artificial intelligence"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z. & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF international conference on computer vision, 10012\u201310022.","key":"135_CR19","DOI":"10.1109\/ICCV48922.2021.00986"},{"doi-asserted-by":"crossref","unstructured":"Wang, R., Ao, J., Zhou, L., Liu, S., Wei, Z., Ko, T. & Zhang, Y. (2022). Multi-view self-attention based transformer for speaker recognition. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6732\u20136736.","key":"135_CR20","DOI":"10.1109\/ICASSP43922.2022.9746639"},{"doi-asserted-by":"crossref","unstructured":"No\u00e9, P.G., Parcollet, T. & Morchid, M. (2020). Cgcnn: Complex gabor convolutional neural network on raw speech. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 7724\u20137728.","key":"135_CR21","DOI":"10.1109\/ICASSP40776.2020.9054220"},{"issue":"16","key":"135_CR22","doi-asserted-by":"publisher","first-page":"4114","DOI":"10.1109\/TSP.2014.2326991","volume":"62","author":"J And\u00e9n","year":"2014","unstructured":"And\u00e9n, J., & Mallat, S. (2014). Deep scattering spectrum. In IEEE Transactions on Signal Processing., 62(16), 4114\u20134128.","journal-title":"In IEEE Transactions on Signal Processing."},{"unstructured":"Balestriero, R., Cosentino, R., Glotin, H. & Baraniuk, R. (2018). Spline filters for end-to-end deep learning. In International conference on machine learning.PMRL., 364\u2013373.","key":"135_CR23"},{"doi-asserted-by":"crossref","unstructured":"Jung, J.W., Heo, H.S., Kim, J.H., Shim, H.J. & Yu, H.J. (2019). Rawnet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification. arXiv., 1904\u201308104.","key":"135_CR24","DOI":"10.21437\/Interspeech.2019-1982"},{"unstructured":"Ba, J.L., Kiros, J.R. & Hinton, G.E. (2016). Layer normalization. arXiv., 1607\u201306450.","key":"135_CR25"},{"unstructured":"Kingma, D.P. & Ba, J. (2014). Adam: A method for stochastic optimization. In 2018 IEEE spoken language technology workshop (SLT), 1412\u20136980.","key":"135_CR26"},{"doi-asserted-by":"crossref","unstructured":"Hoffer, E., Ben-Nun, T., Hubara, I., Giladi, N., Hoefler, T. & Soudry, D. (2020). Augment your batch: Improving generalization through instance repetition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8129\u20138138.","key":"135_CR27","DOI":"10.1109\/CVPR42600.2020.00815"}],"container-title":["Journal of Membrane Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41965-024-00135-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41965-024-00135-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41965-024-00135-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T17:16:03Z","timestamp":1712682963000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41965-024-00135-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["135"],"URL":"https:\/\/doi.org\/10.1007\/s41965-024-00135-2","relation":{},"ISSN":["2523-8906","2523-8914"],"issn-type":[{"type":"print","value":"2523-8906"},{"type":"electronic","value":"2523-8914"}],"subject":[],"published":{"date-parts":[[2024,3]]},"assertion":[{"value":"23 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}