{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T05:01:42Z","timestamp":1742965302670,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533105"},{"type":"electronic","value":"9783031533112"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53311-2_32","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"437-447","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Region Based Non-overlapping Reference Speech Estimation Method for\u00a0Speaker Extraction"],"prefix":"10.1007","author":[{"given":"Yiru","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeke","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bijing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiwei","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"32_CR1","doi-asserted-by":"publisher","first-page":"1370","DOI":"10.1109\/TASLP.2020.2987429","volume":"28","author":"C Xu","year":"2020","unstructured":"Xu, C., Rao, W., Chng, E.S., Li, H.: Spex: multi-scale time domain speaker extraction network. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 1370\u20131384 (2020). https:\/\/doi.org\/10.1109\/TASLP.2020.2987429","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"32_CR2","doi-asserted-by":"publisher","unstructured":"Wang, Q., et al.: VoiceFilter: targeted voice separation by speaker-conditioned spectrogram masking. In: Proceedings of Interspeech 2019, pp. 2728\u20132732 (2019). https:\/\/doi.org\/10.21437\/Interspeech. 2019\u20131101","DOI":"10.21437\/Interspeech"},{"issue":"4","key":"32_CR3","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1109\/JSTSP.2019.2922820","volume":"13","author":"K \u017dmol\u00edkov\u017dmol\u00edkov\u00e1","year":"2019","unstructured":"\u017dmol\u00edkov\u017dmol\u00edkov\u00e1, K., et al.: Speakerbeam: speaker aware neural network for target speaker extraction in speech mixtures. IEEE J. Selected Topics Signal Process. 13(4), 800\u2013814 (2019). https:\/\/doi.org\/10.1109\/JSTSP.2019.2922820","journal-title":"IEEE J. Selected Topics Signal Process."},{"key":"32_CR4","doi-asserted-by":"publisher","unstructured":"\u00d6zg\u00fcr \u00c7etin, Shriberg, E.: Analysis of overlaps in meetings by dialog factors, hot spots, speakers, and collection site: insights for automatic speech recognition. In: Proceedings of Interspeech 2006, pp. paper 1915-Mon2A2O.6 (2006). https:\/\/doi.org\/10.21437\/Interspeech. 2006\u201391","DOI":"10.21437\/Interspeech"},{"key":"32_CR5","doi-asserted-by":"publisher","unstructured":"Chen, Z., et al.: Continuous speech separation: Dataset and analysis. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7284\u20137288 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053426","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"32_CR6","doi-asserted-by":"publisher","unstructured":"Borsdorf, M., Xu, C., Li, H., Schultz, T.: Universal speaker extraction in the presence and absence of target speakers for speech of one and two talkers. In: Proceedings of Interspeech 2021, pp. 1469\u20131473 (2021). https:\/\/doi.org\/10.21437\/Interspeech. 2021\u20131939","DOI":"10.21437\/Interspeech"},{"key":"32_CR7","doi-asserted-by":"publisher","unstructured":"Delcroix, M., Zmol\u00edkov\u00e1, K., Ochiai, T., Kinoshita, K., Nakatani, T.: Speaker activity driven neural speech extraction. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, 6\u201311 June 2021, pp. 6099\u20136103. IEEE (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414998","DOI":"10.1109\/ICASSP39728.2021.9414998"},{"key":"32_CR8","doi-asserted-by":"publisher","first-page":"3032","DOI":"10.1109\/TASLP.2022.3205759","volume":"30","author":"Z Pan","year":"2022","unstructured":"Pan, Z., Ge, M., Li, H.: Usev: universal speaker extraction with visual cue. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 3032\u20133045 (2022). https:\/\/doi.org\/10.1109\/TASLP.2022.3205759","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"32_CR9","doi-asserted-by":"publisher","first-page":"2840","DOI":"10.1109\/TASLP.2021.3099291","volume":"29","author":"N Zeghidour","year":"2021","unstructured":"Zeghidour, N., Grangier, D.: Wavesplit: end-to-end speech separation by speaker clustering. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 2840\u20132849 (2021). https:\/\/doi.org\/10.1109\/TASLP.2021.3099291","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"32_CR10","doi-asserted-by":"publisher","unstructured":"Han, H., Chung, S.W., Kang, H.G.: MIRNet: learning multiple identities representations in overlapped speech. In: Proceedings of Interspeech 2020, pp. 4303\u20134307 (2020). https:\/\/doi.org\/10.21437\/Interspeech. 2020\u20132076","DOI":"10.21437\/Interspeech"},{"key":"32_CR11","doi-asserted-by":"publisher","first-page":"2753","DOI":"10.1109\/TASLP.2021.3101617","volume":"29","author":"J Byun","year":"2021","unstructured":"Byun, J., Shin, J.W.: Monaural speech separation using speaker embedding from preliminary separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 2753\u20132763 (2021). https:\/\/doi.org\/10.1109\/TASLP.2021.3101617","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"32_CR12","doi-asserted-by":"publisher","unstructured":"Han, C., et al.: Continuous speech separation using speaker inventory for long recording. In: Proceedings of Interspeech 2021, pp. 3036\u20133040 (2021). https:\/\/doi.org\/10.21437\/Interspeech. 2021\u2013338","DOI":"10.21437\/Interspeech"},{"key":"32_CR13","doi-asserted-by":"publisher","unstructured":"Wang, P., et al.: Speech separation using speaker inventory. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 230\u2013236 (2019). https:\/\/doi.org\/10.1109\/ASRU46091.2019.9003884","DOI":"10.1109\/ASRU46091.2019.9003884"},{"key":"32_CR14","doi-asserted-by":"publisher","unstructured":"Yu, D., Kolb\u00e6k, M., Tan, Z.H., Jensen, J.: Permutation invariant training of deep models for speaker-independent multi-talker speech separation. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 241\u2013245 (2017). https:\/\/doi.org\/10.1109\/ICASSP.2017.7952154","DOI":"10.1109\/ICASSP.2017.7952154"},{"issue":"6","key":"32_CR15","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR16","doi-asserted-by":"publisher","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an asr corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210 (2015). https:\/\/doi.org\/10.1109\/ICASSP.2015.7178964","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"32_CR17","doi-asserted-by":"publisher","unstructured":"Kao, C.C., Wang, W., Sun, M., Wang, C.: R-CRNN: region-based convolutional recurrent neural network for audio event detection. In: Proc. Interspeech 2018, pp. 1358\u20131362 (2018). https:\/\/doi.org\/10.21437\/Interspeech. 2018\u20132323","DOI":"10.21437\/Interspeech"},{"key":"32_CR18","doi-asserted-by":"publisher","unstructured":"Huang, Z., Watanabe, S., Fujita, Y., Garc\u00eda, P., Shao, Y., Povey, D., Khudanpur, S.: Speaker diarization with region proposal network. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6514\u20136518 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053760","DOI":"10.1109\/ICASSP40776.2020.9053760"},{"key":"32_CR19","unstructured":"Cosentino, J., Pariente, M., Cornell, S., Deleforge, A., Vincent, E.: Librimix: an open-source dataset for generalizable speech separation (2020)"},{"key":"32_CR20","doi-asserted-by":"publisher","unstructured":"Ge, M., Xu, C., Wang, L., Chng, E.S., Dang, J., Li, H.: SpEx+: a Complete Time Domain Speaker Extraction Network. In: Proceedings of Interspeech 2020, pp. 1406\u20131410 (2020). https:\/\/doi.org\/10.21437\/Interspeech. 2020\u20131397","DOI":"10.21437\/Interspeech"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Bredin, H., et al.: pyannote.audio: neural building blocks for speaker diarization. In: ICASSP 2020, IEEE International Conference on Acoustics, Speech, and Signal Processing (2020)","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Bredin, H., Laurent, A.: End-to-end speaker segmentation for overlap-aware resegmentation. In: Proceedings of Interspeech 2021 (2021)","DOI":"10.21437\/Interspeech.2021-560"},{"key":"32_CR23","doi-asserted-by":"publisher","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: emphasized channel attention, propagation and aggregation in tdnn based speaker verification. In: Proceedings of Interspeech 2020, pp. 3830\u20133834 (2020). https:\/\/doi.org\/10.21437\/Interspeech. 2020\u20132650","DOI":"10.21437\/Interspeech"},{"key":"32_CR24","doi-asserted-by":"publisher","unstructured":"Kanda, N., Horiguchi, S., Fujita, Y., Xue, Y., Nagamatsu, K., Watanabe, S.: Simultaneous speech recognition and speaker diarization for monaural dialogue recordings with target-speaker acoustic models. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 31\u201338 (2019). https:\/\/doi.org\/10.1109\/ASRU46091.2019.9004009","DOI":"10.1109\/ASRU46091.2019.9004009"},{"key":"32_CR25","doi-asserted-by":"publisher","unstructured":"Manohar, V., Chen, S.J., Wang, Z., Fujita, Y., Watanabe, S., Khudanpur, S.: Acoustic modeling for overlapping speech recognition: Jhu chime-5 challenge system. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6665\u20136669 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8682556","DOI":"10.1109\/ICASSP.2019.8682556"},{"issue":"6","key":"32_CR26","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: Wavlm: large-scale self-supervised pre-training for full stack speech processing. IEEE J. Selected Topics Signal Process. 16(6), 1505\u20131518 (2022). https:\/\/doi.org\/10.1109\/JSTSP.2022.3188113","journal-title":"IEEE J. Selected Topics Signal Process."},{"key":"32_CR27","doi-asserted-by":"publisher","unstructured":"Roux, J.L., Wisdom, S., Erdogan, H., Hershey, J.R.: Sdr - half-baked or well done? In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 626\u2013630 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683855","DOI":"10.1109\/ICASSP.2019.8683855"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53311-2_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:31:01Z","timestamp":1710257461000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53311-2_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533105","9783031533112"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53311-2_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","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":"112","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":"38% - 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":"3.2","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":"3.2","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)"}}]}}