{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:35:19Z","timestamp":1742945719105,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031780134"},{"type":"electronic","value":"9783031780141"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78014-1_20","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:24:26Z","timestamp":1732191866000},"page":"264-276","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Separating Party Conversation by\u00a0Applying Contrastive Learning Methodology"],"prefix":"10.1007","author":[{"given":"Anandakumar","family":"Singaravelan","sequence":"first","affiliation":[]},{"given":"Jia-Lien","family":"Hsu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"20_CR1","unstructured":"Cosentino, J., Pariente, M., Cornell, S., Deleforge, A., Vincent, E.: Librimix: an open-source dataset for generalizable speech separation (2020)"},{"key":"20_CR2","doi-asserted-by":"publisher","unstructured":"Dabrowski, A., Cetnarowicz, D., Marciniak, T.: Analysis of speech separation for ASR systems. In: Proceedings of the Fourth International Workshop on Robot Motion and Control, IEEE Cat. No.04EX891, pp. 345\u2013350 (2004). https:\/\/doi.org\/10.1109\/ROMOCO.2004.240584","DOI":"10.1109\/ROMOCO.2004.240584"},{"key":"20_CR3","unstructured":"Defossez, A., Usunier, N., Bottou, L., Bach, F.: Music source separation in the waveform domain (2020). https:\/\/openreview.net\/forum?id=HJx7uJStPH"},{"key":"20_CR4","doi-asserted-by":"publisher","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. ACM Trans. Graph. 37(4) (2018). https:\/\/doi.org\/10.1145\/3197517.3201357","DOI":"10.1145\/3197517.3201357"},{"key":"20_CR5","unstructured":"Gajara, D.: Royalty-free audio dataset (2020). https:\/\/www.kaggle.com\/datasets\/darshan1504\/royaltyfree-audio-dataset"},{"key":"20_CR6","doi-asserted-by":"publisher","unstructured":"Hennequin, R., Khlif, A., Voituret, F., Moussallam, M.: Spleeter: a fast and efficient music source separation tool with pre-trained models. J. Open Source Softw. 5(50), 2154 (2020). https:\/\/doi.org\/10.21105\/joss.02154","DOI":"10.21105\/joss.02154"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Isik, Y.Z., Roux, J.L., Chen, Z., Watanabe, S., Hershey, J.R.: Single-channel multi-speaker separation using deep clustering. arXiv preprint arXiv:1607.02173 (2016)","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"20_CR8","doi-asserted-by":"publisher","unstructured":"Luo, Y., Chen, Z., Mesgarani, N.: Speaker-independent speech separation with deep attractor network. IEEE\/ACM Trans. Audio Speech Lang. Proc. 26(4), 787\u2013796 (2018). https:\/\/doi.org\/10.1109\/TASLP.2018.2795749","DOI":"10.1109\/TASLP.2018.2795749"},{"issue":"8","key":"20_CR9","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","volume":"27","author":"Y Luo","year":"2019","unstructured":"Luo, Y., Mesgarani, N.: Conv-TasNet: surpassing ideal time-frequency magnitude masking for speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(8), 1256\u20131266 (2019). https:\/\/doi.org\/10.1109\/TASLP.2019.2915167","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Masuyama, Y., et al.: Exploring the integration of speech separation and recognition with self-supervised learning representation. arXiv preprint arXiv:2307.12231 (2023)","DOI":"10.1109\/WASPAA58266.2023.10248096"},{"key":"20_CR11","doi-asserted-by":"publisher","unstructured":"Petermann, D., Wichern, G., Wang, Z.Q., Roux, J.L.: The cocktail fork problem: three-stem audio separation for real-world soundtracks. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 526\u2013530 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746005","DOI":"10.1109\/ICASSP43922.2022.9746005"},{"key":"20_CR12","unstructured":"Ravanelli, M., et al.: SpeechBrain: a general-purpose speech toolkit. aXiv preprint arXiv:2106.04624 (2021)"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Samuel, D., Ganeshan, A., Naradowsky, J.: Meta-learning extractors for music source separation. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 816\u2013820 (2020). https:\/\/api.semanticscholar.org\/CorpusID:211132471","DOI":"10.1109\/ICASSP40776.2020.9053513"},{"key":"20_CR14","doi-asserted-by":"publisher","unstructured":"Slizovskaia, O., Haro, G., G\u00f3mez, E.: Conditioned source separation for musical instrument performances. IEEE\/ACM Trans. Audio, Speech and Lang. Proc. 29, 2083\u20132095 (2021). https:\/\/doi.org\/10.1109\/TASLP.2021.3082331","DOI":"10.1109\/TASLP.2021.3082331"},{"key":"20_CR15","unstructured":"Snyder, D., Chen, G., Povey, D.: MUSAN: a music, speech, and noise corpus. arXiv preprint arXiv:1510.08484v1 (2015)"},{"key":"20_CR16","unstructured":"Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS\u201916 , pp. 1857\u20131865. Curran Associates Inc., Red Hook, NY, USA (2016)"},{"key":"20_CR17","doi-asserted-by":"publisher","unstructured":"St\u00f6ter, F.R., Uhlich, S., Liutkus, A., Mitsufuji, Y.: Open-Unmix - a reference implementation for music source separation. J. Open Source Softw. 4(41), 1667 (2019). https:\/\/doi.org\/10.21105\/joss.01667","DOI":"10.21105\/joss.01667"},{"key":"20_CR18","doi-asserted-by":"publisher","unstructured":"Subakan, C., Ravanelli, M., Cornell, S., Bronzi, M., Zhong, J.: Attention is all you need in speech separation. In: Proceedings of the ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 21\u201325 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9413901","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"20_CR19","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: Proceedings of the 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"},{"key":"20_CR20","doi-asserted-by":"publisher","unstructured":"Zhang, L., Li, C., Deng, F., Wang, X.: Multi-task audio source separation. In: 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 671\u2013678 (2021). https:\/\/doi.org\/10.1109\/ASRU51503.2021.9687922","DOI":"10.1109\/ASRU51503.2021.9687922"},{"key":"20_CR21","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Chen, C., Chen, H.H., Liu, X., Hu, Y., Chng, E.S.: Noise-aware speech separation with contrastive learning. In: Proceedings of the ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1381\u20131385 (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10448214","DOI":"10.1109\/ICASSP48485.2024.10448214"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78014-1_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T15:07:23Z","timestamp":1736348843000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78014-1_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031780134","9783031780141"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78014-1_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","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":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","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":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}