{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:03:41Z","timestamp":1743141821289,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030602758"},{"type":"electronic","value":"9783030602765"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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":[[2020]]},"DOI":"10.1007\/978-3-030-60276-5_5","type":"book-chapter","created":{"date-parts":[[2020,10,4]],"date-time":"2020-10-04T07:02:44Z","timestamp":1601794964000},"page":"45-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Directional Clustering with Polyharmonic Phase Estimation for Enhanced Speaker Localization"],"prefix":"10.1007","author":[{"given":"Sergei","family":"Astapov","sequence":"first","affiliation":[]},{"given":"Dmitriy","family":"Popov","sequence":"additional","affiliation":[]},{"given":"Vladimir","family":"Kabarov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"5_CR1","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-99579-3_3","volume-title":"Speech and Computer","author":"S Astapov","year":"2018","unstructured":"Astapov, S., Lavrentyev, A., Shuranov, E.: Far field speech enhancement at low SNR in presence of nonstationary noise based on spectral masking and MVDR beamforming. In: Karpov, A., Jokisch, O., Potapova, R. (eds.) SPECOM 2018. LNCS (LNAI), vol. 11096, pp. 21\u201331. Springer, Cham (2018). \nhttps:\/\/doi.org\/10.1007\/978-3-319-99579-3_3"},{"key":"5_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-030-26061-3_4","volume-title":"Speech and Computer","author":"S Astapov","year":"2019","unstructured":"Astapov, S., et al.: Acoustic event mixing to multichannel AMI data for distant speech recognition and acoustic event classification benchmarking. In: Salah, A.A., Karpov, A., Potapova, R. (eds.) SPECOM 2019. LNCS (LNAI), vol. 11658, pp. 31\u201342. Springer, Cham (2019). \nhttps:\/\/doi.org\/10.1007\/978-3-030-26061-3_4"},{"key":"5_CR3","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.specom.2018.03.009","volume":"99","author":"SY Barysenka","year":"2018","unstructured":"Barysenka, S.Y., Vorobiov, V.I., Mowlaee, P.: Single-channel speech enhancement using inter-component phase relations. Speech Commun. 99, 144\u2013160 (2018)","journal-title":"Speech Commun."},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Comanducci, L., Cobos, M., Antonacci, F., Sarti, A.: Time difference of arrival estimation from frequency-sliding generalized cross-correlations using convolutional neural networks. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4945\u20134949 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053429"},{"key":"5_CR5","series-title":"Springer Briefs in Speech Technology","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73059-2","volume-title":"Direction of Arrival Estimation and Localization of Multi-Speech Sources","author":"N Dey","year":"2017","unstructured":"Dey, N., Ashour, A.: Direction of Arrival Estimation and Localization of Multi-Speech Sources. Springer Briefs in Speech Technology. Springer, Cham (2017). \nhttps:\/\/doi.org\/10.1007\/978-3-319-73059-2"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"DiBiase, J.H.: A High-Accuracy, Low-Latency Technique for Talker Localization in Reverberant Environments Using Microphone Arrays. Ph.D. thesis, Brown University, Providence, RI, USA (2000)","DOI":"10.1007\/978-3-662-04619-7_8"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Do, H., Silverman, H.F.: Stochastic particle filtering: a fast SRP-PHAT single source localization algorithm. In: 2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, pp. 213\u2013216 (2009)","DOI":"10.1109\/ASPAA.2009.5346540"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"He, W., Lu, L., Zhang, B., Mahadeokar, J., Kalgaonkar, K., Fuegen, C.: Spatial attention for far-field speech recognition with deep beamforming neural networks. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7499\u20137503, May 2020","DOI":"10.1109\/ICASSP40776.2020.9053439"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Ito, N., Araki, S., Nakatani, T.: Complex angular central Gaussian mixture model for directional statistics in mask-based microphone array signal processing. In: 2016 24th European Signal Processing Conference (EUSIPCO), pp. 1153\u20131157 (2016)","DOI":"10.1109\/EUSIPCO.2016.7760429"},{"issue":"5","key":"5_CR10","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1109\/LSP.2014.2365040","volume":"22","author":"J Kulmer","year":"2015","unstructured":"Kulmer, J., Mowlaee, P.: Phase estimation in single channel speech enhancement using phase decomposition. IEEE Signal Process. Lett. 22(5), 598\u2013602 (2015)","journal-title":"IEEE Signal Process. Lett."},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Luo, Y., Han, C., Mesgarani, N., Ceolini, E., Liu, S.C.: FaSNet: Low-latency adaptive beamforming for multi-microphone audio processing. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 260\u2013267. IEEE, Piscataway, NJ (2020). IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2019); Conference Location: Singapore, Singapore; Conference Date: December 14\u201318 (2019)","DOI":"10.1109\/ASRU46091.2019.9003849"},{"key":"5_CR12","unstructured":"Sachar, J.M.: Some Important Algorithms for Large-Aperture Microphone Arrays: Calibration and Determination of Talker Orientation. Ph.D. thesis, Brown University, Providence, RI, USA (2004)"},{"issue":"5 Pt 1","key":"5_CR13","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1121\/1.1471895","volume":"111","author":"HF Silverman","year":"2002","unstructured":"Silverman, H.F., Patterson, W.R., Sachar, J.: Factors affecting the performance of large-aperture microphone arrays. J. Acoust. Soc. Am. 111(5 Pt 1), 2140\u20132157 (2002)","journal-title":"J. Acoust. Soc. Am."},{"key":"5_CR14","doi-asserted-by":"publisher","first-page":"3418","DOI":"10.3390\/s18103418","volume":"18","author":"J Vera-Diaz","year":"2018","unstructured":"Vera-Diaz, J., Pizarro, D., Macias-Guarasa, J.: Towards end-to-end acoustic localization using deep learning: from audio signals to source position coordinates. Sensors 18, 3418 (2018)","journal-title":"Sensors"},{"key":"5_CR15","first-page":"11","volume":"3","author":"VI Vorobiov","year":"2012","unstructured":"Vorobiov, V.I., Davydov, A.G.: Study of the relations between quasi-harmonic components of speech signal in Chinese language. Proc. Twenty-Fifth Session Russian Acoust. Soc. 3, 11\u201314 (2012)","journal-title":"Proc. Twenty-Fifth Session Russian Acoust. Soc."},{"issue":"4","key":"5_CR16","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1109\/JSTSP.2019.2925640","volume":"13","author":"S Watanabe","year":"2019","unstructured":"Watanabe, S., Araki, S., Bacchiani, M., Haeb-Umbach, R., Seltzer, M.L.: Introduction to the issue on far-field speech processing in the era of deep learning: speech enhancement, separation, and recognition. IEEE J. Sel. Top. Sig. Process. 13(4), 785\u2013786 (2019)","journal-title":"IEEE J. Sel. Top. Sig. Process."},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Xiao, X., Watanabe, S., Chng, E.S., Li, H.: Beamforming networks using spatial covariance features for far-field speech recognition. In: 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 1\u20136 (2016)","DOI":"10.1109\/APSIPA.2016.7820724"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zarar, S., Tashev, I., Lee, C.H.: Convolutional-recurrent neural networks for speech enhancement. In: IEEE International Conference Acoustics Speech and Signal Processing (ICASSP), April 2018","DOI":"10.1109\/ICASSP.2018.8462155"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60276-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,4]],"date-time":"2020-10-04T07:03:01Z","timestamp":1601794981000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60276-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602758","9783030602765"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60276-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St. Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"160","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"65","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the Corona pandemic SPECOM 2020 was held as a virtual event","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}