{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:51:57Z","timestamp":1740099117700,"version":"3.37.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319995786"},{"type":"electronic","value":"9783319995793"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-99579-3_70","type":"book-chapter","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T07:36:09Z","timestamp":1535096169000},"page":"687-696","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Lightweight Embeddings for Speaker Verification"],"prefix":"10.1007","author":[{"given":"Maxim","family":"Tkachenko","sequence":"first","affiliation":[]},{"given":"Alexander","family":"Yamshinin","sequence":"additional","affiliation":[]},{"given":"Mikhail","family":"Kotov","sequence":"additional","affiliation":[]},{"given":"Marina","family":"Nastasenko","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,25]]},"reference":[{"key":"70_CR1","doi-asserted-by":"crossref","unstructured":"Heigold, G., Moreno, I., Bengio, S., Shazeer, N.: End-to-end text-dependent speaker verification. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Shanghai, China (2016)","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"70_CR2","unstructured":"David, S., Pegah, G., Daniel, P., Daniel, G.R., Yishay, C., Sanjeev K.: Neural network-based speaker embeddings for end-to-end speaker verification. In: IEEE Spoken Language Technology Workshop (SLT), San Diego, California (2016)"},{"key":"70_CR3","doi-asserted-by":"crossref","unstructured":"Schroff, F., Philbin, J.: FaceNet: A unified embedding for face recognition and clustering. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"issue":"8","key":"70_CR4","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"6","key":"70_CR5","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition. IEEE Sig. Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Sig. Process. Mag."},{"key":"70_CR6","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference for Learning Representations, San Diego (2015)"},{"key":"70_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., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19, 788\u2013798 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"70_CR8","doi-asserted-by":"crossref","unstructured":"Prince, S.J., Elder, J.H.: Probabilistic linear discriminant analysis for inferences about identity. In: 11th International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, pp. 1\u20138 (2007)","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"70_CR9","doi-asserted-by":"crossref","unstructured":"Cumani, S., Laface, P., Torino, P.: Probabilistic linear discriminant analysis of i-vector posterior distributions. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, Canada (2013)","DOI":"10.1109\/ICASSP.2013.6639150"},{"key":"70_CR10","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Weiss, R.J., Senior, A., Wilson, K.W., Vinyals, O.: Learning the speech front-end with raw waveform CLDNNs. In: 16th Annual Conference of the International Speech Communication Association (INTERSPEECH), Dresden, Germany (2015)","DOI":"10.21437\/Interspeech.2015-1"},{"key":"70_CR11","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"70_CR12","unstructured":"Jozefowicz, R., Zaremba W., Sutskever, I.: An empirical exploration of recurrent network architectures. In: International Conference on Machine Learning (ICML), Lille, France (2015)"},{"key":"70_CR13","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yang, D., Dyer Chr., He, X., Smola, A., Hovy, E.: Hierarchical attention networks for document classification. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, California (2016)","DOI":"10.18653\/v1\/N16-1174"},{"key":"70_CR14","doi-asserted-by":"crossref","unstructured":"Luong, M., Pham, H., Christopher, M.: Effective approaches to attention-based neural machine translation. In: Empirical Methods in Natural Language Processing (EMNLP), Lisbon, Portugal (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"70_CR15","unstructured":"Li., Ch., et al.: Deep speaker: an end-to-end neural speaker embedding system. In: IEEE Spoken Language Technology Workshop (SLT), San Diego, California (2016)"},{"key":"70_CR16","doi-asserted-by":"crossref","unstructured":"Cao, Z., Long, M., Wang, J., Yu, P.: HashNet: deep learning to hash by continuation. In: IEEE International Conference on Computer Vision (ICCV), Venice, Italy (2017)","DOI":"10.1109\/ICCV.2017.598"},{"key":"70_CR17","unstructured":"NIST SRE. https:\/\/www.nist.gov\/itl\/iad\/mig\/speaker-recognition"},{"key":"70_CR18","unstructured":"Testarium: Research tool. http:\/\/testarium.makseq.com"},{"key":"70_CR19","unstructured":"TfMicro: Tensorflow binding. http:\/\/github.com\/makseq\/tfmicro"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99579-3_70","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T05:03:12Z","timestamp":1661835792000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99579-3_70"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319995786","9783319995793"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99579-3_70","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}