{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:41:29Z","timestamp":1757619689333,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819698042"},{"type":"electronic","value":"9789819698059"}],"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_8","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T05:53:44Z","timestamp":1753422824000},"page":"86-97","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Alignment Losses for End-to-End Speaker Diarization"],"prefix":"10.1007","author":[{"given":"Simeng","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhida","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihua","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaochen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317","volume":"72","author":"TJ Park","year":"2022","unstructured":"Park, T.J., Kanda, N., Dimitriadis, D., Han, K.J., Watanabe, S., Narayanan, S.: A review of speaker diarization: Recent advances with deep learning. Comput. Speech Lang. 72, 101317 (2022)","journal-title":"Comput. Speech Lang."},{"issue":"3","key":"8_CR2","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1109\/TASLP.2017.2769220","volume":"26","author":"G Gelly","year":"2017","unstructured":"Gelly, G., Gauvain, J.L.: Optimization of rnn-based speech activity detection. IEEE\/ACM Trans. Audio Speech Lang. Process. 26(3), 646\u2013656 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"8","key":"8_CR3","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1109\/LSP.2004.831666","volume":"11","author":"J Ajmera","year":"2004","unstructured":"Ajmera, J., McCowan, I., Bourlard, H.: Robust speaker change detection. IEEE Sign. Process. Lett. 11(8), 649\u2013651 (2004)","journal-title":"IEEE Sign. Process. Lett."},{"issue":"4","key":"8_CR4","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":"8_CR5","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":"8_CR6","doi-asserted-by":"crossref","unstructured":"Lee, E.P., Sun, G., Zhang, C., Woodland, P.C.: Spectral clustering-aware learning of embeddings for speaker diarisation. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096993"},{"key":"8_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254","volume":"71","author":"F Landini","year":"2022","unstructured":"Landini, F., Profant, J., Diez, M., Burget, L.: Bayesian hmm clustering of x-vector sequences (vbx) in speaker diarization: theory, implementation and analysis on standard tasks. Comput. Speech Lang. 71, 101254 (2022)","journal-title":"Comput. Speech Lang."},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Fujita, Y., Kanda, N., Horiguchi, S., Xue, Y., Nagamatsu, K., Watanabe, S.: End-to-end neural speaker diarization with self-attention. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). pp. 296\u2013303. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Fujita, Y., Kanda, N., Horiguchi, S., Nagamatsu, K., Watanabe, S.: End-to-end neural speaker diarization with permutation-free objectives. arXiv preprint arXiv:1909.05952 (2019)","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Yu, Y., Park, D., Kim, H.K.: Auxiliary loss of transformer with residual connection for end-to-end speaker diarization. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 8377\u20138381. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746602"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Horiguchi, S., Fujita, Y., Watanabe, S., Xue, Y., Nagamatsu, K.: End-to-end speaker diarization for an unknown number of speakers with encoder-decoder based attractors. arXiv preprint arXiv:2005.09921 (2020)","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Kinoshita, K., Delcroix, M., Tawara, N.: Advances in integration of end-to-end neural and clustering-based diarization for real conversational speech. arXiv preprint arXiv:2105.09040 (2021)","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"8_CR13","unstructured":"Wang, T., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: International Conference on Machine Learning. pp. 9929\u20139939. PMLR (2020)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Godfrey, J.J., Holliman, E.C., McDaniel, J.: Switchboard: telephone speech corpus for research and development. In: Acoustics, Speech, and Signal Processing, IEEE International Conference on. vol. 1, pp. 517\u2013520. IEEE Computer Society (1992)","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"8_CR15","unstructured":"Przybocki, M., Martin, A.F.: Nist speaker recognition evaluation chronicles. In: The Speaker and Language Recognition Workshop (Odyssey 2004). pp. 15\u201322 (2004)"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Martin, A., Przybocki, M., Campbell Jr, J.P.: The nist speaker recognition evaluation program. In: Biometric systems: Technology, Design and Performance Evaluation, pp. 241\u2013262. Springer (2005)","DOI":"10.1007\/1-84628-064-8_8"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Przybocki, M.A., Martin, A.F., Le, A.N.: Nist speaker recognition evaluation chronicles-part 2. In: 2006 IEEE Odyssey-The Speaker and Language Recognition Workshop. pp. 1\u20136. IEEE (2006)","DOI":"10.1109\/ODYSSEY.2006.248120"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Martin, A.F., Greenberg, C.S.: Nist 2008 speaker recognition evaluation: Performance across telephone and room microphone channels. In: Tenth Annual Conference of the International Speech Communication Association (2009)","DOI":"10.21437\/Interspeech.2009-679"},{"key":"8_CR19","unstructured":"Snyder, D., Chen, G., Povey, D.: Musan: A Music, Speech, and Noise Corpus. arXiv preprint arXiv:1510.08484 (2015)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Seltzer, M.L., Khudanpur, S.: A study on data augmentation of reverberant speech for robust speech recognition. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 5220\u20135224 (2017)","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"8_CR21","unstructured":"Przybocki, M., Martin, A.: 2000 nist speaker recognition evaluation. In: Philadelphia: Linguistic Data Consortium (2001)"}],"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_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T22:34:26Z","timestamp":1757284466000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9805-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698042","9789819698059"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9805-9_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}