{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T11:40:34Z","timestamp":1781610034602,"version":"3.54.5"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-17017-x","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T05:02:11Z","timestamp":1701752531000},"page":"54433-54448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Speech refinement using Bi-LSTM and improved spectral clustering in speaker diarization"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1416-3252","authenticated-orcid":false,"given":"Aishwarya","family":"Gupta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Archana","family":"Purwar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,12,5]]},"reference":[{"key":"17017_CR1","doi-asserted-by":"publisher","first-page":"101317","DOI":"10.1016\/j.csl.2021.101317","volume":"72","author":"TJ Park","year":"2022","unstructured":"Park TJ, Kanda N, Dimitriadis D, Han KJ, Watanabe S, Narayanan S (2022) A review of speaker diarization: Recent advances with deep learning. Comput Speech Lang 72:101317. https:\/\/doi.org\/10.1016\/j.csl.2021.101317","journal-title":"Comput Speech Lang"},{"issue":"2","key":"17017_CR2","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","volume":"20","author":"X Anguera","year":"2012","unstructured":"Anguera X, Bozonnet S, Evans N, Fredouille C, Friedland G, Vinyals O (2012) Speaker diarization: A review of recent research. IEEE Trans Audio Speech Lang Process 20(2):356\u2013370. https:\/\/doi.org\/10.1109\/TASL.2011.2125954","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"17017_CR3","doi-asserted-by":"crossref","unstructured":"Sun L, Du J, Jiang C, Zhang X, He S, Yin B, Lee C (2018) Speaker diarization with enhancing speech for the first DIHARD challenge. Interspeech","DOI":"10.21437\/Interspeech.2018-1742"},{"key":"17017_CR4","doi-asserted-by":"crossref","unstructured":"Sinclair M, King S (2013) Where are the challenges in speaker diarization?. In: 2013 IEEE International conference on acoustics, speech and signal processing. IEEE, pp 7741\u20137745","DOI":"10.1109\/ICASSP.2013.6639170"},{"key":"17017_CR5","first-page":"1455","volume":"4","author":"R Sarikaya","year":"1998","unstructured":"Sarikaya R, Hansen JH (1998) December). Robust detection of speech activity in the presence of noise. Proc ICSLP 4:1455\u20131458","journal-title":"Proc ICSLP"},{"key":"17017_CR6","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.csl.2005.08.002","volume":"20","author":"S Meignier","year":"2006","unstructured":"Meignier S, Moraru D, Fredouille C, Bonastre J-F, Besacier L (2006) Stepby-step and integrated approaches in broadcast news speaker diarization. Comput Speech Lang 20:303\u2013330","journal-title":"Comput Speech Lang"},{"key":"17017_CR7","unstructured":"Chen S, Gopalakrishnan P (1998) Speaker, environment and channel change detection and clustering via the bayesian information criterion. In Proc. DARPA broadcast news transcription and understanding workshop, vol. 8.\u00a0DARPA, pp 127\u2013132"},{"key":"17017_CR8","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/S0167-6393(00)00027-3","volume":"32","author":"P Delacourt","year":"2000","unstructured":"Delacourt P, Wellekens CJ (2000) Distbic: A speaker-based segmentation for audio data indexing. Speech Commun 32:111\u2013126","journal-title":"Speech Commun"},{"key":"17017_CR9","doi-asserted-by":"crossref","unstructured":"Senoussaoui M, Kenny P, Stafylakis T, Dumouchel P (2013) A study of the cosine distance-based mean shift for telephone speech diarization. IEEE\/ACM Trans Audio Speech Lang Process 22:217\u2013227","DOI":"10.1109\/TASLP.2013.2285474"},{"key":"17017_CR10","doi-asserted-by":"crossref","unstructured":"Landini F, Glembek O, Mat\u011bjka P, Rohdin J, Burget L, Diez M, Silnova A (2021) Analysis of the but diarization system for voxconverse challenge. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 5819\u20135823","DOI":"10.1109\/ICASSP39728.2021.9414315"},{"key":"17017_CR11","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). IEEE, pp 5329\u20135333","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"17017_CR12","doi-asserted-by":"publisher","unstructured":"Landini Federico et al. (2021) Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation, and analysis on standard tasks. Comput Speech Lang. https:\/\/doi.org\/10.1016\/j.csl.2021.101254","DOI":"10.1016\/j.csl.2021.101254"},{"key":"17017_CR13","doi-asserted-by":"crossref","unstructured":"Sell G, Garcia-Romero D (2014) Speaker diarization with PLDA i-vector scoring and unsupervised calibration. In: 2014 IEEE Spoken Language Technology Workshop (SLT). IEEE, pp 413\u2013417","DOI":"10.1109\/SLT.2014.7078610"},{"key":"17017_CR14","doi-asserted-by":"crossref","unstructured":"Kang W, Roy BC, Chow W (2020) Multimodal speaker diarization of real-world meetings using d-vectors with spatial features. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).\u00a0IEEE, pp 6509\u20136513\u00a0","DOI":"10.1109\/ICASSP40776.2020.9053122"},{"key":"17017_CR15","doi-asserted-by":"crossref","unstructured":"Novoselov S, Gusev A, Ivanov A, Pekhovsky T, Shulipa A, Avdeeva A et al (2019) Speaker diarization with deep speaker embeddings for DIHARD challenge II. In: Interspeech. pp 1003\u20131007","DOI":"10.21437\/Interspeech.2019-2757"},{"key":"17017_CR16","doi-asserted-by":"publisher","unstructured":"Comaniciu, Meer P (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24(5):603\u2013619. https:\/\/doi.org\/10.1109\/34.1000236","DOI":"10.1109\/34.1000236"},{"key":"17017_CR17","first-page":"7","volume":"2","author":"T Stafylakis","year":"2010","unstructured":"Stafylakis T, Katsouros V, Carayannis G (2010) Speaker clustering via the mean shift algorithm. ReCALL 2:7","journal-title":"ReCALL"},{"key":"17017_CR18","doi-asserted-by":"crossref","unstructured":"Han KJ, Narayanan SS (2007) A robust stopping criterion for agglomerative hierarchical clustering in a speaker diarization system. In: Interspeech. pp 1853\u20131856","DOI":"10.21437\/Interspeech.2007-516"},{"key":"17017_CR19","doi-asserted-by":"publisher","unstructured":"Von Luxburg U (2007) A tutorial on spectral clustering. Stat Comput 17:395\u2013416. https:\/\/doi.org\/10.1007\/s11222-007-9033-z","DOI":"10.1007\/s11222-007-9033-z"},{"key":"17017_CR20","doi-asserted-by":"publisher","unstructured":"Ng A, Jordan M, Weiss Y (2001) On spectral clustering: Analysis and an algorithm. Adv Neural Inf Process Syst 14:849\u2013856. https:\/\/dl.acm.org\/doi\/abs\/https:\/\/doi.org\/10.5555\/2980539.2980649","DOI":"10.5555\/2980539.2980649"},{"key":"17017_CR21","doi-asserted-by":"crossref","unstructured":"Ning H, Liu M, Tang H, Huang TS (2006) A spectral clustering approach to speaker diarization. In: Ninth international conference on spoken language processing","DOI":"10.21437\/Interspeech.2006-566"},{"key":"17017_CR22","unstructured":"Luque J, Hernando J (2012) On the use of agglomerative and spectral clustering in speaker diarization of meetings. In: Odyssey 2012-The speaker and language recognition workshop"},{"key":"17017_CR23","doi-asserted-by":"crossref","unstructured":"Park TJ, Han KJ, Kumar M, Narayanan S (2019) Auto-tuning spectral clustering for speaker diarization using normalized maximum eigengap. IEEE Signal Process Lett 27:381\u2013385. https:\/\/arxiv.org\/abs\/2003.02405","DOI":"10.1109\/LSP.2019.2961071"},{"key":"17017_CR24","unstructured":"Zelnik-Manor L, Perona P (2004) Self-tuning spectral clustering. Adv Neural Inform Proc Syst 17"},{"key":"17017_CR25","doi-asserted-by":"publisher","unstructured":"Shum Stephen H et al (2013) Unsupervised methods for speaker diarization: An integrated and iterative approach. IEEE Trans Audio Speech Lang Process 21.10:2015\u20132028. https:\/\/doi.org\/10.1109\/TASL.2013.2264673","DOI":"10.1109\/TASL.2013.2264673"},{"key":"17017_CR26","doi-asserted-by":"crossref","unstructured":"Rouvier M, Bousquet PM, Favre B (2015) Speaker diarization through speaker embeddings. In: 2015 23rd European Signal Processing Conference (eusipco). IEEE, pp 2082\u20132086","DOI":"10.1109\/EUSIPCO.2015.7362751"},{"key":"17017_CR27","doi-asserted-by":"crossref","unstructured":"Toruk M, Bilgin G, Serbes A (2020) Speaker diarization using embedding vectors. In 2020 28th Signal Processing and Communications Applications Conference (SIU). IEEE, pp 1\u20134","DOI":"10.1109\/SIU49456.2020.9302162"},{"key":"17017_CR28","doi-asserted-by":"crossref","unstructured":"Sun G, Liu D, Zhang C, &Woodland PC (2021) Content-aware speaker embeddings for speaker diarisation. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 7168\u20137172","DOI":"10.1109\/ICASSP39728.2021.9414390"},{"key":"17017_CR29","doi-asserted-by":"crossref","unstructured":"Zhang A, Wang Q, Zhu Z, Paisley J, Wang C (2019) Fully supervised speaker diarization. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 6301\u20136305","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"17017_CR30","doi-asserted-by":"crossref","unstructured":"Wang Q, Downey C, Wan L, Mansfield PA, Moreno IL (2018) Speaker diarization with LSTM. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 5239\u20135243","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"17017_CR31","doi-asserted-by":"crossref","unstructured":"Nakanishi I, Nagata Y, Itoh Y, Fukui Y (2006) Single-channel speech enhancement based on frequency domain ALE. In: 2006 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, pp 4","DOI":"10.1109\/ISCAS.2006.1693141"},{"key":"17017_CR32","unstructured":"Li W (2008) Effective post-processing for single-channel frequency-domain speech enhancement. In: 2008 IEEE International conference on multimedia and expo. IEEE, pp 149\u2013152"},{"key":"17017_CR33","doi-asserted-by":"publisher","unstructured":"Parchami M, Zhu WP, Champagne B, Plourde E (2016) Recent developments in speech enhancement in the short-timeFourier transform domain. IEEE Circ Syst Mag 16(3):45\u201377. https:\/\/doi.org\/10.1109\/MCAS.2016.2583681","DOI":"10.1109\/MCAS.2016.2583681"},{"issue":"2","key":"17017_CR34","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1109\/LSP.2003.821714","volume":"11","author":"Y Hu","year":"2004","unstructured":"Hu Y, Loizou PC (2004) Incorporating a psycho acoustical model in frequency domain speech enhancement. IEEE Signal Process Lett 11(2):270\u2013273","journal-title":"IEEE Signal Process Lett"},{"key":"17017_CR35","doi-asserted-by":"publisher","unstructured":"Hu Y, Loizou PC (2004b) Speech enhancement based on wavelet thresholding the multi-taper spectrum. IEEE Trans Speech Audio Process 12(1):59\u201367. https:\/\/doi.org\/10.1109\/tsa.2003.819949","DOI":"10.1109\/tsa.2003.819949"},{"key":"17017_CR36","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"SF Boll","year":"1979","unstructured":"Boll SF (1979) Suppression of Acoustic Noise in Speech Using Spectral Subtraction. IEEE Trans Acoust Speech Signal Process 27:113\u2013120. https:\/\/doi.org\/10.1109\/TASSP.1979.1163209","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"17017_CR37","doi-asserted-by":"publisher","unstructured":"Upadhyay N, Karmakar A (2015) Speech enhancement using spectral subtraction-type algorithms: A comparison and simulation study. Procedia Comput Sci 54:574\u2013584. https:\/\/doi.org\/10.1016\/j.procs.2015.06.066","DOI":"10.1016\/j.procs.2015.06.066"},{"key":"17017_CR38","doi-asserted-by":"publisher","unstructured":"Abd El-Fattah MA, Dessouky MI, Abbas AM et al (2014) Speech enhancement with an adaptive Wiener filter. Int J Speech Technol 53\u201364. https:\/\/doi.org\/10.1007\/s10772-013-9205-5","DOI":"10.1007\/s10772-013-9205-5"},{"key":"17017_CR39","doi-asserted-by":"publisher","unstructured":"Pandey A, Wang DL, Fellow IEEE (2019) A new framework or CNN-based speech enhancement in the time domain. IEEE Trans Audio Speech Lang Process 27(7):1179\u20131188. https:\/\/doi.org\/10.1109\/taslp.2019.2913512","DOI":"10.1109\/taslp.2019.2913512"},{"key":"17017_CR40","doi-asserted-by":"crossref","unstructured":"Yu H, Ouyang Z, Zhu WP, Champagne B, Ji Y (2019) A deep neural network based Kalman filter for time domain speech enhancement. In: 2019 IEEE International Symposium on Circuits And Systems (ISCAS). IEEE, pp 1\u20135","DOI":"10.1109\/ISCAS.2019.8702161"},{"key":"17017_CR41","unstructured":"Sainburg T (2018) Noise reduction using spectral gating in python. Tim Sain-burg"},{"key":"17017_CR42","unstructured":"Ng A, Jordan M, Weiss Y (2001) On spectral clustering: analysis and an algorithm. Adv Neural Inform Proc Syst 14"},{"key":"17017_CR43","doi-asserted-by":"crossref","unstructured":"Xia W, Lu H, Wan Q, Tripathi A, Huang Y, Moreno IL, Sak H (2022) Turn-to-diarize: online speaker diarization constrained by transformer transducer speaker turn detection. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 8077\u20138081","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"key":"17017_CR44","first-page":"2","volume":"6","author":"SG Mihov","year":"2009","unstructured":"Mihov SG, Ivanov RM, Popov AN (2009) Denoising speech signals by wavelet transform. Annual J Electron 6:2\u20135","journal-title":"Annual J Electron"},{"key":"17017_CR45","unstructured":"Kumariss VSR, Devarakonda Dileep Kumar (2023) A Wavelet Based Denoising of Speech Signal. Int J Eng Trends Technol (IJETT) V5(2):107\u2013115. ISSN:2231\u20135381"},{"issue":"13","key":"17017_CR46","doi-asserted-by":"publisher","first-page":"45","DOI":"10.5120\/16858-6739","volume":"96","author":"N Kaladharan","year":"2014","unstructured":"Kaladharan N (2014) Speech enhancement by spectral subtraction method. Int J Comput Applic 96(13):45\u201348. https:\/\/doi.org\/10.5120\/16858-6739","journal-title":"Int J Comput Applic"},{"key":"17017_CR47","doi-asserted-by":"publisher","first-page":"32","DOI":"10.4236\/jsip.2014.52006","volume":"5","author":"M Karam","year":"2014","unstructured":"Karam M et al (2014) Noise removal in speech processing using spectral subtraction. J Signal Inf Process 5:32\u201341. https:\/\/doi.org\/10.4236\/jsip.2014.52006","journal-title":"J Signal Inf Process"},{"key":"17017_CR48","doi-asserted-by":"crossref","unstructured":"Ahmad R, Zubair S, Alquhayz H, Ditta A (2019) Multimodal speaker diarization using a pre-trained audio-visual synchronization model. Sensors 19(23):5163. https:\/\/www.mdpi.com\/1424-8220\/19\/23\/5163","DOI":"10.3390\/s19235163"},{"key":"17017_CR49","doi-asserted-by":"publisher","unstructured":"Ahmad R, Zubair S, Alquhayz H (2020) Speech enhancement for multimodal speaker diarization system. IEEE Access 8:126671\u2013126680. https:\/\/doi.org\/10.1109\/ACCESS.2020.3007312","DOI":"10.1109\/ACCESS.2020.3007312"},{"key":"17017_CR50","doi-asserted-by":"crossref","unstructured":"Gupta A, Purwar A (2022) Enhancing speaker diarization for audio-only systems using deep learning. In: Applications of artificial intelligence, big data and internet of things in sustainable development. CRC Press. pp 65\u201379","DOI":"10.1201\/9781003245469-5"},{"key":"17017_CR51","doi-asserted-by":"publisher","unstructured":"Das N, Chakraborty S, Chaki J, Dey N (2021) Fundamentals, present and future perspectives of speech enhancement. Int J Speech Technol 24(4):883\u2013901. https:\/\/doi.org\/10.1007\/s10772-020-09674-2","DOI":"10.1007\/s10772-020-09674-2"},{"key":"17017_CR52","doi-asserted-by":"crossref","unstructured":"Islam MR, Rahman MF, Khan MAG (2009) Improvement of speech enhancement techniques for robust speaker identification in noise. In: 2009 12th International conference on computers and information technology. IEEE, pp 255\u2013260","DOI":"10.1109\/ICCIT.2009.5407130"},{"key":"17017_CR53","unstructured":"D\u00e9fossez A, Usunier N, Bottou L, Bach F (2019) Music source separation in the waveform domain. arXiv preprint arXiv:1911.13254"},{"key":"17017_CR54","doi-asserted-by":"crossref","unstructured":"Defossez A et al (2020) Real time speech enhancement in the waveform domain.\u00a0Interspeech","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"17017_CR55","unstructured":"D\u00e9fossez A, Usunier N, Bottou L, Bach F (2019) Demucs: deep extractor for music sources with extra unlabeled data remixed. arXiv preprint arXiv:1909.01174"},{"key":"17017_CR56","unstructured":"Stoller Daniel, Ewert Sebastian, Dixon Simon (2018) Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation. URL https:\/\/arxiv.org\/abs\/1806.03185"},{"key":"17017_CR57","unstructured":"https:\/\/www.kaggle.com\/code\/mauriciofigueiredo\/methods-for-sound-noise-reduction\/notebook."},{"issue":"1","key":"17017_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10618-012-0291-9","volume":"28","author":"X Wang","year":"2014","unstructured":"Wang X, Qian B, Davidson I (2014) On constrained spectral clustering and its applications. Data Min Knowl Disc 28(1):1\u201330","journal-title":"Data Min Knowl Disc"},{"issue":"2","key":"17017_CR59","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1109\/TKDE.2014.2356471","volume":"27","author":"J Li","year":"2014","unstructured":"Li J, Xia Y, Shan Z, Liu Y (2014) Scalable constrained spectral clustering. IEEE Trans Knowl Data Eng 27(2):589\u2013593","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"17017_CR60","doi-asserted-by":"crossref","unstructured":"Raj D, Huang Z, Khudanpur S (2021) Multi-class spectral clustering with overlaps for speaker diarization. In: 2021 IEEE Spoken Language Technology workshop (SLT). IEEE, pp 582\u2013589","DOI":"10.1109\/SLT48900.2021.9383602"},{"issue":"3","key":"17017_CR61","first-page":"4","volume":"2","author":"Z Huang","year":"2019","unstructured":"Huang Z, Zhou JT, Peng X, Zhang C, Zhu H, Lv J (2019) Multi-view spectral clustering network. IJCAI 2(3):4","journal-title":"Multi-view spectral clustering network. IJCAI"},{"key":"17017_CR62","doi-asserted-by":"crossref","unstructured":"Nagrani A, Chung JS, Zisserman A (2017) VoxCeleb: a large-scale speaker identification dataset. Interspeech","DOI":"10.21437\/Interspeech.2017-950"},{"key":"17017_CR63","doi-asserted-by":"crossref","unstructured":"Chung Joon Son, Nagrani Arsha, Zisserman Andrew (2018) Voxceleb2: Deep speaker recognition. arXiv preprint arXiv:1806.05622","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"17017_CR64","doi-asserted-by":"crossref","unstructured":"Chung Joon Son et al (2020) Spot the conversation: speaker diarisation in the wild. arXiv preprint arXiv:2007.01216. Interspeech","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"17017_CR65","unstructured":"(2017) Herve Bredin, pyannote. metrics: a toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems. Hypothesis 100(60):90"},{"issue":"9","key":"17017_CR66","doi-asserted-by":"publisher","first-page":"4161","DOI":"10.3390\/app1209416","volume":"12","author":"Z Kang","year":"2022","unstructured":"Kang Z, Huang Z, Lu C (2022) Speech Enhancement Using U-Net with Compressed Sensing. Appl Sci 12(9):4161. https:\/\/doi.org\/10.3390\/app1209416","journal-title":"Appl Sci"},{"key":"17017_CR67","unstructured":"Macartney Craig, Weyde Tillman (2018) Improved speech enhancement with the wave-u-net. arXiv preprint arXiv:1811.11307"},{"key":"17017_CR68","doi-asserted-by":"publisher","unstructured":"Gupta A, Purwar A (2022) Analysis of clustering algorithms for Speaker Diarization using LSTM. 2022 1st International Conference on Informatics (ICI), Noida, India, pp. 19\u201324. https:\/\/doi.org\/10.1109\/ICI53355.2022.9786928","DOI":"10.1109\/ICI53355.2022.9786928"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17017-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17017-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17017-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:22:47Z","timestamp":1730766167000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17017-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":68,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["17017"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-17017-x","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,5]]},"assertion":[{"value":"11 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}