{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T11:41:21Z","timestamp":1765280481318,"version":"3.44.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s10772-025-10201-4","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T09:51:01Z","timestamp":1752141061000},"page":"597-609","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Direct normalized cut clustering using a novel robust cluster estimation technique for multi-speaker diarization"],"prefix":"10.1007","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1416-3252","authenticated-orcid":false,"given":"Aishwarya","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8824-4859","authenticated-orcid":false,"given":"Archana","family":"Purwar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,9]]},"reference":[{"key":"10201_CR1","doi-asserted-by":"crossref","unstructured":"Aishwarya, G., & Archana, P. (2022). Proceedings of 2022 1st international conference on informatics (ICI): April 14\u201316, 2022. In Proceedings of 2022 1st international conference on informatics (ICI 2022), (p. 254) IEEE.","DOI":"10.1109\/ICI53355.2022.9786873"},{"key":"10201_CR2","unstructured":"Anguera, X. & Bozonnet, S., et al. (2010). Speaker diarization: A review of recent research. IEEE Transactions on Acoustics, Speech, and Signal Processing."},{"key":"10201_CR3","doi-asserted-by":"crossref","unstructured":"Aronowitz, H., Zhu, W., Suzuki, M., Kurata, G., & Hoory, R. (2020). New advances in speaker diarization. INTERSPEECH, 279\u2013283.","DOI":"10.21437\/Interspeech.2020-1879"},{"key":"10201_CR4","doi-asserted-by":"publisher","unstructured":"Bredin, H. (2017). Pyannote. Metrics: A toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems. In Proceedings of the annual conference of the international speech communication association, Interspeech, (pp. 3587\u20133591). International Speech Communication Association. https:\/\/doi.org\/10.21437\/Interspeech.2017-411","DOI":"10.21437\/Interspeech.2017-411"},{"key":"10201_CR5","unstructured":"Bredin, H. (2022). Pyannote. Audio: Neural building blocks for speaker diarization. ICASSP, [Online]. Available. http:\/\/arxiv.org\/abs\/1911.01255."},{"key":"10201_CR6","unstructured":"Chung, F. R. K. (1997). Lectures on spectral graph theory. American Mathematical Society, 92."},{"key":"10201_CR7","doi-asserted-by":"publisher","unstructured":"Chung, J. S., Huh, J., Nagrani, A., Afouras, T., & Zisserman, A. (2020). Spot the conversation: Speaker diarisation in the wild. In Proceedings of the annual conference of the international speech communication association, Interspeech, (pp. 299\u2013303). International Speech Communication Association. https:\/\/doi.org\/10.21437\/Interspeech.2020-2337","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"10201_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-981-15-1209-4_1","volume-title":"Communications in computer and information science","author":"D. T. Dinh","year":"2019","unstructured":"Dinh, D. T., Fujinami, T., & Huynh, V. N. (2019). Estimating the optimal number of clusters in categorical data clustering by silhouette coefficient. Communications in computer and information science, Springer Science and Business Media Deutschland GmbH. 1\u201317. https:\/\/doi.org\/10.1007\/978-981-15-1209-4_1."},{"key":"10201_CR9","doi-asserted-by":"crossref","unstructured":"Gregory, S. (2014). Speaker diarization with PLDA i-vector scoring and unsupervised calibration. In IEEE spoken language technology workshop (SLT), (pp. 413\u2013417). IEEE.","DOI":"10.1109\/SLT.2014.7078610"},{"key":"10201_CR10","doi-asserted-by":"publisher","first-page":"1493","DOI":"10.1109\/TASLP.2022.3162080","volume":"30","author":"S. Horiguchi","year":"2022","unstructured":"Horiguchi, S., Fujita, Y., Watanabe, S., Xue, Y., & Garcia, P. (2022). Encoder-decoder based attractors for end-to-end neural diarization, IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 30, 1493\u20131507. https:\/\/doi.org\/10.1109\/TASLP.2022.3162080","journal-title":"IEEE\/ACM trans audio speech lang process"},{"key":"10201_CR11","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14097187","author":"S. B. Kalluri","year":"2024","unstructured":"Kalluri, S. B., et al. (2025). The second displace challenge: Diarization of speaker and language in conversational environments. In ICASSP, Jun. 2024: May 13, 2025. Available: https:\/\/doi.org\/10.5281\/zenodo.14097187","journal-title":"ICASSP, Jun"},{"key":"10201_CR12","doi-asserted-by":"crossref","unstructured":"Kang, W., Roy, B. C., & Chow, W. (2020). Multimodal speaker diarization of real-world meetings using d-vectors with spatial features. In 2020 IEEE international conference on acoustics, speech and signal processing (ICASSP 2020).","DOI":"10.1109\/ICASSP40776.2020.9053122"},{"key":"10201_CR13","doi-asserted-by":"publisher","unstructured":"Kinoshita, K., Delcroix, M., & Tawara, N. (2021). Advances in integration of end-to-end neural and clustering-based diarization for real conversational speech. In Proceedings of the annual conference of the international speech communication association, INTERSPEECH, (pp. 2513\u20132517). International Speech Communication Association. https:\/\/doi.org\/10.21437\/Interspeech.2021-1004","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"10201_CR14","doi-asserted-by":"publisher","unstructured":"Landini, F., Profant, J., Diez, M., & Burget, L. (2020). Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: Theory, implementation, and analysis on standard tasks. Computer Speech and Language, 71, 101254. https:\/\/doi.org\/10.1016\/j.csl.2021.101254","DOI":"10.1016\/j.csl.2021.101254"},{"issue":"6","key":"10201_CR15","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1016\/j.patcog.2011.12.017","volume":"45","author":"J. Liang","year":"2012","unstructured":"Liang, J., Zhao, X., Li, D., Cao, F., & Dang, C. (2012). Determining the number of clusters using information entropy for mixed data. Pattern Recognition, 45(6):2251\u20132265. https:\/\/doi.org\/10.1016\/j.patcog.2011.12.017","journal-title":"Pattern recognition"},{"key":"10201_CR16","unstructured":"Lopez-Otero, P., Docio-Fernandez, L., & Garcia-Mateo, C. (2014). A novel method for selecting the number of clusters in a speaker diarization system. In 22nd European signal processing conference (EUSIPCO), (pp. 656\u2013660)."},{"key":"10201_CR17","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s11222-007-9033-z","volume":"17","author":"U. V. Luxburg","year":"2007","unstructured":"Luxburg, U. V. (2007). A tutorial on spectral clustering. Statitics Computation, 17, 395\u2013416. Available: http:\/\/arxiv.org\/abs\/0711.0189","journal-title":"Stat Computation"},{"key":"10201_CR18","unstructured":"Mccowan, I., et al. (2005). The AMI meeting corpus. In International conference on methods and techniques on behavioral research. [Online]. Available: https:\/\/www.amiproject.org\/"},{"key":"10201_CR19","unstructured":"Ng, A. Y., & Jordan, M. I. (2001). On spectral clustering: Analysis and an algorithm. In NIPS\u201901: Proceedings of the 15th international conference on neural information processing systems: Natural and synthetic, (pp. 849\u2013856)."},{"key":"10201_CR20","doi-asserted-by":"publisher","unstructured":"O\u2019Shaughnessy, D. (2025). Speaker diarization: A review of objectives and methods. Applied Science, 15, 4. https:\/\/doi.org\/10.20944\/preprints","DOI":"10.20944\/preprints"},{"key":"10201_CR21","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1109\/LSP.2019.2961071","volume":"27","author":"T. J. Park","year":"2020","unstructured":"Park, T. J., Han, K. J., Kumar, M., & Narayanan, S. (2020). Auto-tuning spectral clustering for speaker diarization using normalized maximum eigengap. IEEE Signal Processintg Letters, 27, 381\u2013385. https:\/\/doi.org\/10.1109\/LSP.2019.2961071","journal-title":"IEEE Signal process lett"},{"key":"10201_CR22","doi-asserted-by":"crossref","unstructured":"Park, T. J., Kanda, N., Dimitriadis, D., Han, K. J., Watanabe, S., & Narayanan, S. (2021). A review of speaker diarization: Recent advances with deep learning. Computer Speech and Language, 72, 101317. Available: http:\/\/arxiv.org\/abs\/2101.09624","DOI":"10.1016\/j.csl.2021.101317"},{"key":"10201_CR23","unstructured":"Povey, D., et al. (2011). The Kaldi speech recognition toolkit. IEEE Workshop on Automatic Speech Recognition and Understanding [Online]. Available: http:\/\/kaldi.sf.net\/"},{"key":"10201_CR24","doi-asserted-by":"publisher","unstructured":"Raj, D., Huang, Z., & Khudanpur, S. (2021). Multi-class spectral clustering with overlaps for speaker diarization. In 2021 IEEE spoken language technology workshop - Proceedings (SLT 2021) (pp. 582\u2013589). Institute of Electrical and Electronics Engineers Inc. https:\/\/doi.org\/10.1109\/SLT48900.2021.9383602","DOI":"10.1109\/SLT48900.2021.9383602"},{"key":"10201_CR25","first-page":"87","volume-title":"Data clustering","author":"C. K. Reddy","year":"2014","unstructured":"Reddy, C. K., & Vinzamuri, B. (2014). A survey of partitional and hierarchical clustering algorithms, Data clustering, 1st, Chapman and Hall\/CRC. 87\u2013110.","edition":"1st"},{"key":"10201_CR26","doi-asserted-by":"publisher","unstructured":"Selvarajah, J. (2022). Overlapped speech detection for improved speaker diarization on tamil dataset. In SLAAI international conference on artificial intelligence (SLAAI-ICAI-2022)., IEEE. https:\/\/doi.org\/10.1109\/SLAAI-ICAI56923.2022.10002438","DOI":"10.1109\/SLAAI-ICAI56923.2022.10002438"},{"issue":"8","key":"10201_CR27","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J. Shi","year":"2000","unstructured":"Shi, J., & Malik, J. (2000). Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888\u2013905.","journal-title":"IEEE Transactions on pattern analysis and machine intelligence"},{"key":"10201_CR28","doi-asserted-by":"crossref","unstructured":"Singh, P., & Ganapathy, S. (2024). End-to-end supervised hierarchical graph clustering for speaker diarization. IEEE Transaction on Audio, Speech and Language Processing, [Online]. Available: http:\/\/arxiv.org\/abs\/2401.12850","DOI":"10.1109\/TASLPRO.2025.3525967"},{"key":"10201_CR29","doi-asserted-by":"crossref","unstructured":"Singh, P., Kaul, A., & Ganapathy, S. (2023). Supervised hierarchical clustering using graph neural networks for speaker diarization. In ICAASP, Feb. 2023. [Online]. Available: http:\/\/arxiv.org\/abs\/2302.12716","DOI":"10.1109\/ICASSP49357.2023.10095372"},{"key":"10201_CR30","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  IEEE international conference on acoustics, speech and signal processing (ICASSP 2018), (pp. 5329\u20135333). Available: http:\/\/www.openslr.org","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"10201_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Q., Downey, C., Wan, L., Mansfield, P. A., & Moreno, I. L. (2018). Speaker diarization with LSTM. In IEEE international conference on acoustics, speech and signal processing (ICASSP 2018), (pp. 5239\u20135243). Available: http:\/\/arxiv.org\/abs\/1710.10468","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"10201_CR32","doi-asserted-by":"crossref","unstructured":"Yu, S. X., & Shi, J. (2003). Multiclass spectral clustering. In Proceedings ninth IEEE international conference on computer vision. (pp. 313\u2013319).","DOI":"10.1109\/ICCV.2003.1238361"},{"key":"10201_CR33","unstructured":"Zelnik-Manor, L., & Perona, P. (2004). Self-tuning spectral clustering. Advances in Neural Information Processing Systems, 17. Available: http:\/\/www.vision.caltech.edu\/lihi\/Demos\/SelfTuningClustering.html"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-025-10201-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-025-10201-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-025-10201-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T03:04:43Z","timestamp":1757214283000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-025-10201-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10201"],"URL":"https:\/\/doi.org\/10.1007\/s10772-025-10201-4","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2025,6]]},"assertion":[{"value":"31 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author declares that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}