{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:20:21Z","timestamp":1781713221454,"version":"3.54.5"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Research Foundation - Flander","award":["G081420N"],"award-info":[{"award-number":["G081420N"]}]},{"DOI":"10.13039\/100012331","name":"VLAIO)","doi-asserted-by":"crossref","award":["imec.ICON: BLE2AV"],"award-info":[{"award-number":["imec.ICON: BLE2AV"]}],"id":[{"id":"10.13039\/100012331","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Speaker embeddings, from the ECAPA-TDNN speaker verification network, were recently introduced as features for the task of clustering microphones in ad hoc arrays. Our previous work demonstrated that, in comparison to signal-based Mod-MFCC features, using speaker embeddings yielded a more robust and logical clustering of the microphones around the sources of interest. This work aims to further establish speaker embeddings as a robust feature for ad hoc microphone clustering by addressing open and additional questions of practical interest, arising from our prior work. Specifically, whereas our initial work made use of simulated data based on shoe-box acoustics models, we now present a more thorough analysis in more realistic settings. Furthermore, we investigate additional important considerations such as the choice of the distance metric used in the fuzzy C-means clustering; the minimal time range across which data need to be aggregated to obtain robust clusters; and the performance of the features in increasingly more challenging situations, and with multiple speakers. We also contrast the results on the basis of several metrics for quantifying the quality of such ad hoc clusters. Results indicate that the speaker embeddings are robust to short inference times, and deliver logical and useful clusters, even when the sources are very close to each other.<\/jats:p>","DOI":"10.1186\/s13636-023-00310-w","type":"journal-article","created":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T08:02:33Z","timestamp":1698739353000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Robustness of ad hoc microphone clustering using speaker embeddings: evaluation under realistic and challenging scenarios"],"prefix":"10.1186","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9300-4251","authenticated-orcid":false,"given":"Stijn","family":"Kindt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jenthe","family":"Thienpondt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Becker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nilesh","family":"Madhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,31]]},"reference":[{"key":"310_CR1","doi-asserted-by":"crossref","unstructured":"A.\u00a0Bertrand, in 2011 18th IEEE symposium on communications and vehicular technology in the Benelux (SCVT), Applications and trends in wireless acoustic sensor networks: A signal processing perspective (IEEE, 2011), pp. 1\u20136","DOI":"10.1109\/SCVT.2011.6101302"},{"key":"310_CR2","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.sigpro.2014.04.034","volume":"107","author":"S Gergen","year":"2015","unstructured":"S. Gergen, A. Nagathil, R. Martin, Classification of reverberant audio signals using clustered ad hoc distributed microphones. Sig. Process. 107, 21\u201332 (2015)","journal-title":"Sig. Process."},{"key":"310_CR3","doi-asserted-by":"crossref","unstructured":"A.J. Mu\u00f1oz-Montoro, P.\u00a0Vera-Candeas, M.G. Christensen, in 2021 29th European Signal Processing Conference (EUSIPCO), A coherence-based clustering method for multichannel speech enhancement in wireless acoustic sensor networks (IEEE, 2021), pp. 1130\u20131134","DOI":"10.23919\/EUSIPCO54536.2021.9616074"},{"issue":"4","key":"310_CR4","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/TASL.2010.2055560","volume":"19","author":"I Himawan","year":"2010","unstructured":"I. Himawan, I. McCowan, S. Sridharan, Clustered blind beamforming from ad-hoc microphone arrays. IEEE Trans. Audio Speech Lang. Process. 19(4), 661\u2013676 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"310_CR5","unstructured":"S.\u00a0Gergen, R.\u00a0Martin, N.\u00a0Madhu, in Speech Communication; 13th ITG-Symposium, Source separation by fuzzy-membership value aware beamforming and masking in ad hoc arrays (VDE, 2018), pp. 1\u20135"},{"key":"310_CR6","doi-asserted-by":"crossref","unstructured":"S.\u00a0Pasha, Y.X. Zou, C.\u00a0Ritz, in 2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP), Forming ad-hoc microphone arrays through clustering of acoustic room impulse responses (IEEE, 2015), pp. 84\u201388","DOI":"10.1109\/ChinaSIP.2015.7230367"},{"issue":"6","key":"310_CR7","doi-asserted-by":"publisher","first-page":"4189","DOI":"10.1121\/10.0001449","volume":"147","author":"Y Zhao","year":"2020","unstructured":"Y. Zhao, J.K. Nielsen, J. Chen, M.G. Christensen, Model-based distributed node clustering and multi-speaker speech presence probability estimation in wireless acoustic sensor networks. J. Acoust. Soc. Am. 147(6), 4189\u20134201 (2020)","journal-title":"J. Acoust. Soc. Am."},{"key":"310_CR8","doi-asserted-by":"publisher","unstructured":"M.\u00a0Dziubany, R.\u00a0Machhamer, H.\u00a0Laux, A.\u00a0Schmeink, K.U. Gollmer, G.\u00a0Burger, G.\u00a0Dartmann, in 2018 26th European Signal Processing Conference (EUSIPCO), Machine learning based indoor localization using a representative k-nearest-neighbor classifier on a low-cost iot-hardware (2018), pp. 2050\u20132054. https:\/\/doi.org\/10.23919\/EUSIPCO.2018.8553155","DOI":"10.23919\/EUSIPCO.2018.8553155"},{"key":"310_CR9","unstructured":"S.\u00a0Gergen, R.\u00a0Martin, in Speech Communication; 12. ITG Symposium, Estimating source dominated microphone clusters in ad-hoc microphone arrays by fuzzy clustering in the feature space (VDE, 2016), pp. 1\u20135"},{"key":"310_CR10","doi-asserted-by":"crossref","unstructured":"S.\u00a0Gergen, R.\u00a0Martin, N.\u00a0Madhu, in 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC), Source separation by feature-based clustering of microphones in ad hoc arrays (IEEE, 2018), pp. 530\u2013534","DOI":"10.1109\/IWAENC.2018.8521301"},{"key":"310_CR11","doi-asserted-by":"crossref","unstructured":"A.\u00a0Nelus, R.\u00a0Glitza, R.\u00a0Martin, in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Estimation of microphone clusters in acoustic sensor networks using unsupervised federated learning (IEEE, 2021), pp. 761\u2013765","DOI":"10.1109\/ICASSP39728.2021.9414186"},{"key":"310_CR12","doi-asserted-by":"crossref","unstructured":"L.\u00a0Becker, A.\u00a0Nelus, R.\u00a0Glitza, R.\u00a0Martin, in 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), Accelerated unsupervised clustering in acoustic sensor networks using federated learning and a variational autoencoder (IEEE, 2022), pp. 1\u20135","DOI":"10.1109\/IWAENC53105.2022.9914753"},{"key":"310_CR13","doi-asserted-by":"crossref","unstructured":"S.\u00a0Kindt, J.\u00a0Thienpondt, N.\u00a0Madhu, in ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Exploiting speaker embeddings for improved microphone clustering and speech separation in ad-hoc microphone arrays (IEEE, 2023), pp. 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10094862"},{"key":"310_CR14","doi-asserted-by":"crossref","unstructured":"B.\u00a0Desplanques, J.\u00a0Thienpondt, K.\u00a0Demuynck, in Interspeech 2020, ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in TDNN based speaker verification (International Speech Communication Association (ISCA), 2020), pp. 3830\u20133834","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"310_CR15","doi-asserted-by":"crossref","unstructured":"R. Glitza, L. Becker, A. Nelus, R. Martin, In: 2023 31st European Signal Processing Conference (EUSIPCO), Database of simulated room impulse responses for acoustic sensor networks deployed in complex multi-source acoustic environments. (IEEE, 2023), pp. 246\u2013250","DOI":"10.23919\/EUSIPCO58844.2023.10290083"},{"issue":"4","key":"310_CR16","first-page":"1","volume":"2004","author":"F Bimbot","year":"2004","unstructured":"F. Bimbot, J.F. Bonastre, C. Fredouille, G. Gravier, I. Magrin-Chagnolleau, S. Meignier, T. Merlin, J. Ortega-Garc\u00eda, D. Petrovska-Delacr\u00e9taz, D.A. Reynolds, A tutorial on text-independent speaker verification. EURASIP J. Adv. Signal Proc. 2004(4), 1\u201322 (2004)","journal-title":"EURASIP J. Adv. Signal Proc."},{"issue":"8","key":"310_CR17","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1016\/j.specom.2011.05.007","volume":"53","author":"PN Garner","year":"2011","unstructured":"P.N. Garner, Cepstral normalisation and the signal to noise ratio spectrum in automatic speech recognition. Speech Commun. 53(8), 991\u20131001 (2011)","journal-title":"Speech Commun."},{"key":"310_CR18","doi-asserted-by":"publisher","unstructured":"D.\u00a0Snyder, D.\u00a0Garcia-Romero, G.\u00a0Sell, D.\u00a0Povey, S.\u00a0Khudanpur, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), X-vectors: Robust dnn embeddings for speaker recognition (2018), pp. 5329\u20135333. https:\/\/doi.org\/10.1109\/ICASSP.2018.8461375","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"310_CR19","doi-asserted-by":"publisher","unstructured":"J.\u00a0Hu, L.\u00a0Shen, G.\u00a0Sun, in 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Squeeze-and-excitation networks (2018), pp. 7132\u20137141. https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"310_CR20","doi-asserted-by":"publisher","unstructured":"J.\u00a0Deng, J.\u00a0Guo, N.\u00a0Xue, S.\u00a0Zafeiriou, in 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Arcface: Additive angular margin loss for deep face recognition (2019), pp. 4685\u20134694. https:\/\/doi.org\/10.1109\/CVPR.2019.00482","DOI":"10.1109\/CVPR.2019.00482"},{"issue":"2\u20133","key":"310_CR21","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/0098-3004(84)90020-7","volume":"10","author":"JC Bezdek","year":"1984","unstructured":"J.C. Bezdek, R. Ehrlich, W. Full, FCM: The fuzzy c-means clustering algorithm. Comput. Geosci. 10(2\u20133), 191\u2013203 (1984)","journal-title":"Comput. Geosci."},{"key":"310_CR22","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.sigpro.2014.07.014","volume":"107","author":"S Markovich-Golan","year":"2015","unstructured":"S. Markovich-Golan, A. Bertrand, M. Moonen, S. Gannot, Optimal distributed minimum-variance beamforming approaches for speech enhancement in wireless acoustic sensor networks. Signal Process. 107, 4\u201320 (2015)","journal-title":"Signal Process."},{"key":"310_CR23","doi-asserted-by":"crossref","unstructured":"D.\u00a0Cherkassky, S.\u00a0Markovich-Golan, S.\u00a0Gannot, in 2015 23rd European Signal Processing Conference (EUSIPCO), Performance analysis of mvdr beamformer in wasn with sampling rate offsets and blind synchronization (IEEE, 2015), pp. 245\u2013249","DOI":"10.1109\/EUSIPCO.2015.7362382"},{"key":"310_CR24","doi-asserted-by":"crossref","unstructured":"S.\u00a0Rickard, O.\u00a0Yilmaz, in 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol.\u00a01, On the approximate W-disjoint orthogonality of speech (IEEE, 2002), p. 529","DOI":"10.1109\/ICASSP.2002.1005793"},{"key":"310_CR25","unstructured":"G. Dekkers, S. Lauwereins, B. Thoen, M.W. Adhana, H. Brouckxon, B. Van den Bergh, T. Van Waterschoot, B. Vanrumste, M. Verhelst, P. Karsmakers, in 2017 IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE), The sins database for detection of daily activities in a home environment using an acoustic sensor network (IEEE, 2017), pp. 32-36"},{"key":"310_CR26","unstructured":"B.I. Dalenb\u00e4ck. TUCT v2.0e:1, CATT (1999). http:\/\/www.catt.se. Accessed 2019"},{"key":"310_CR27","doi-asserted-by":"crossref","unstructured":"V.\u00a0Panayotov, G.\u00a0Chen, D.\u00a0Povey, S.\u00a0Khudanpur, in 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), Librispeech: an asr corpus based on public domain audio books (IEEE, 2015), pp. 5206\u20135210","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"310_CR28","doi-asserted-by":"crossref","unstructured":"A.\u00a0Nelus, R.\u00a0Glitza, R.\u00a0Martin, in 2021 29th European Signal Processing Conference (EUSIPCO), Unsupervised clustered federated learning in complex multi-source acoustic environments (IEEE, 2021), pp. 1115\u20131119","DOI":"10.23919\/EUSIPCO54536.2021.9615980"},{"key":"310_CR29","doi-asserted-by":"crossref","unstructured":"J.S. Chung, A. Nagrani, A. Zisserman, in Interspeech 2018, Voxceleb2: Deep speaker recognition (International Speech Communication Association (ISCA), 2018), pp. 1086\u20131090","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"310_CR30","doi-asserted-by":"publisher","unstructured":"M.L.D. Dias. Fuzzy $$c$$-means: An implementation of fuzzy $$c$$-means clustering algorithm (2019). https:\/\/doi.org\/10.5281\/zenodo.3066222. https:\/\/git.io\/fuzzy-c-means","DOI":"10.5281\/zenodo.3066222"},{"issue":"4","key":"310_CR31","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"E. Vincent, R. Gribonval, C. F\u00e9votte, Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462\u20131469 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"310_CR32","doi-asserted-by":"crossref","unstructured":"C.H. Taal, R.C. Hendriks, R. Heusdens, J. Jensen, in 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), A short-time objective intel- ligibility measure for time-frequency weighted noisy speech (IEEE, 2010), pp. 4214\u20134217","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"310_CR33","doi-asserted-by":"crossref","unstructured":"A.W. Rix, J.G. Beerends, M.P. Hollier, A.P. Hekstra, in 2001 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., vol. 2, Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs (IEEE, 2001), pp. 749\u2013752","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"310_CR34","doi-asserted-by":"crossref","unstructured":"E.A. Habets, J.\u00a0Benesty, S.\u00a0Gannot, I.\u00a0Cohen, in Speech processing in modern communication, The MVDR beamformer for speech enhancement (Springer, 2010), pp. 225\u2013254","DOI":"10.1007\/978-3-642-11130-3_9"},{"key":"310_CR35","doi-asserted-by":"crossref","unstructured":"Z.Q. Wang, J.\u00a0Le\u00a0Roux, J.R. Hershey, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Multi-channel deep clustering: Discriminative spectral and spatial embeddings for speaker-independent speech separation (IEEE, 2018), pp. 1\u20135","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"310_CR36","doi-asserted-by":"crossref","unstructured":"J.\u00a0Thienpondt, N.\u00a0Madhu, K.\u00a0Demuynck, in 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Margin-mixup: A method for robust speaker verification in multi-speaker audio (IEEE, 2023)","DOI":"10.1109\/ICASSP49357.2023.10095305"}],"updated-by":[{"DOI":"10.1186\/s13636-023-00319-1","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T00:00:00Z","timestamp":1705276800000}}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-023-00310-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13636-023-00310-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-023-00310-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T03:14:09Z","timestamp":1730430849000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-023-00310-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["310"],"URL":"https:\/\/doi.org\/10.1186\/s13636-023-00310-w","relation":{"correction":[{"id-type":"doi","id":"10.1186\/s13636-023-00319-1","asserted-by":"object"}]},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,31]]},"assertion":[{"value":"25 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2024","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1186\/s13636-023-00319-1","URL":"https:\/\/doi.org\/10.1186\/s13636-023-00319-1","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"46"}}