{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:21Z","timestamp":1740122841612,"version":"3.37.3"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,8,3]],"date-time":"2021-08-03T00:00:00Z","timestamp":1627948800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,3]],"date-time":"2021-08-03T00:00:00Z","timestamp":1627948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s10772-021-09875-3","type":"journal-article","created":{"date-parts":[[2021,8,3]],"date-time":"2021-08-03T13:03:55Z","timestamp":1627995835000},"page":"1101-1112","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Unsupervised speech separation by detecting speaker changeover points under single channel condition"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6502-7015","authenticated-orcid":false,"given":"M. K.","family":"Prasanna Kumar","sequence":"first","affiliation":[]},{"given":"R.","family":"Kumaraswamy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,3]]},"reference":[{"key":"9875_CR1","unstructured":"Boldt, J. B., & Ellis, D. P. (2009). A simple correlation based model of intelligibility for nonlinear speech enhancement and separation. In 17th IEEE Europian Signal Processing Conference, 24\u201328th August 2009. Glassgow, UK"},{"issue":"8","key":"9875_CR2","doi-asserted-by":"publisher","first-page":"1424","DOI":"10.1109\/TASLP.2016.2558822","volume":"24","author":"J Du","year":"2016","unstructured":"Du, J., Tu, Y., Dai, L. R., & Lee, C. H. (2016). A regression approach to single-channel speech separation via high-resolution deep neural networks. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 24(8), 1424\u20131437.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"9875_CR3","unstructured":"Ellis, D. (2006). Model based scene analysis. Principles, Algorithms and Applications. Wiley\/IEEEPress."},{"issue":"3","key":"9875_CR4","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1109\/TCSI.2012.2215735","volume":"60","author":"B Gao","year":"2012","unstructured":"Gao, B., Woo, W. L., & Dlay, S. S. (2012). Unsupervised single-channel separation of nonstationary signals using gammatone filterbank and itakura\u2013saito nonnegative matrix two-dimensional factorizations. IEEE Transactions on Circuits and Systems i: Regular Papers, 60(3), 662\u2013675.","journal-title":"IEEE Transactions on Circuits and Systems i: Regular Papers"},{"key":"9875_CR6","first-page":"1365","volume":"4","author":"GJ Jang","year":"2003","unstructured":"Jang, G. J., & Lee, T. W. (2003). A maximum likelihood approach to single-channel source separation. The Journal of Machine Learning Research, 4, 1365\u20131392.","journal-title":"The Journal of Machine Learning Research"},{"key":"9875_CR7","unstructured":"Karhunen, J., & Oja, E. (2001). Independent component analysis. Wiley."},{"key":"9875_CR8","doi-asserted-by":"crossref","unstructured":"Kristjansson, T., Attias, H. and Hershey, J., 2004, May. Single microphone source separation using high resolution signal reconstruction. In 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing (Vol. 2, pp. 817\u2013820). IEEE, (ICASSP\u201904), Montreal, QC, Canada","DOI":"10.1109\/ICASSP.2004.1326383"},{"key":"9875_CR9","doi-asserted-by":"publisher","unstructured":"Luo, Y., Chen, Z., & Yoshioka, T. (2020). Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp.\u00a046\u201350), Barcelona. https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054266.","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"issue":"4","key":"9875_CR10","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/s10772-015-9309-1","volume":"18","author":"MK Prasanna Kumar","year":"2015","unstructured":"Prasanna Kumar, M. K., & Kumaraswamy, R. (2015). Supervised and unsupervised separation of convolutive speech mixtures using f0 and formant frequencies. International Journal of Speech Technology, 18(4), 649\u2013662. https:\/\/doi.org\/10.1007\/s10772-015-9309-1","journal-title":"International Journal of Speech Technology"},{"issue":"1","key":"9875_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10772-016-9381-1","volume":"20","author":"MK Prasanna Kumar","year":"2017","unstructured":"Prasanna Kumar, M. K., & Kumaraswamy, R. (2017a). An unsupervised approach for cochannel speech separation using Hilbert-Huang transform and fuzzy C-means clustering. International Journal of Speech Technology, 20(1), 1\u201313. https:\/\/doi.org\/10.1007\/s10772-016-9381-1","journal-title":"International Journal of Speech Technology"},{"issue":"1","key":"9875_CR12","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s10772-016-9392-y","volume":"20","author":"MK Prasanna Kumar","year":"2017","unstructured":"Prasanna Kumar, M. K., & Kumaraswamy, R. (2017b). Single-channel speech separation using Empirical Mode Decomposition and multi pitch information with estimation of number of speakers. International Journal of Speech Technology, 20(1), 109\u2013125. https:\/\/doi.org\/10.1007\/s10772-016-9392-y","journal-title":"International Journal of Speech Technology"},{"issue":"4","key":"9875_CR13","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.1007\/s10772-017-9468-3","volume":"20","author":"MK Prasanna Kumar","year":"2017","unstructured":"Prasanna Kumar, M. K., & Kumaraswamy, R. (2017c). Single-channel speech separation using Combined EMD and speech-specific information. International Journal of Speech Technology, 20(4), 1037\u20131047. https:\/\/doi.org\/10.1007\/s10772-017-9468-3","journal-title":"International Journal of Speech Technology"},{"issue":"5","key":"9875_CR14","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1049\/ietspr.2016.0450","volume":"11","author":"MK Prasanna Kumar","year":"2017","unstructured":"Prasanna Kumar, M. K., & Kumaraswamy, R. (2017d). Single channel speech separation based on Empirical Mode Decomposition and Hilbert transform. IET Signal Processing, 11(5), 579\u2013586. https:\/\/doi.org\/10.1049\/ietspr.2016.0450","journal-title":"IET Signal Processing"},{"key":"9875_CR15","doi-asserted-by":"crossref","unstructured":"Schmidt, M. N., & Olsson, R. K. (2017). Single channel speech separation using sparse non negative matrix factorization. In Proc Int. Conf. Spoken Lang.Process. (INTERSPEECH) (pp.\u00a02614-2617). Pittsburgh, PA, 2006 pp. 2614\u20132617.","DOI":"10.21437\/Interspeech.2006-655"},{"issue":"2","key":"9875_CR16","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1109\/TASL.2010.2047419","volume":"19","author":"M Stark","year":"2010","unstructured":"Stark, M., Wohlmayr, M., & Pernkopf, F. (2010). Source\u2013filter-based single-channel speech separation using pitch information. IEEE Transactions on Audio, Speech, and Language Processing, 19(2), 242\u2013255.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9875_CR17","doi-asserted-by":"crossref","unstructured":"Taal, C. H., Hendriks, R. C., Heusdens, R., & Jensen, J. (2011). An algorithm for intelligibility prediction of time-frequency weighted noisy speech. In IEEE Transactions on Audio, Speech, and Language Processing.","DOI":"10.1109\/ICASSP.2010.5495701"},{"issue":"11","key":"9875_CR18","doi-asserted-by":"publisher","first-page":"1722","DOI":"10.1109\/TNNLS.2013.2258680","volume":"24","author":"N Tengtrairat","year":"2013","unstructured":"Tengtrairat, N., Gao, B., Woo, W. L., & Dlay, S. S. (2013). Single-channel blind separation using pseudo-stereo mixture and complex 2-D histogram. IEEE Transactions on Neural Networks and Learning Systems, 24(11), 1722\u20131735.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"9875_CR19","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent, E., Gribonval, R., & F\u00e9votte, C. (2006). Performance measurement in blind audio source separation. IEEE Transactions on Audio, Speech, and Language Processing, 14(4), 1462\u20131469.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"9875_CR20","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1109\/TASL.2006.885253","volume":"15","author":"T Virtanen","year":"2007","unstructured":"Virtanen, T. (2007). Monaural sound source separation by non-negative matrix factorization with temporal continuity and sparseness criteria. IEEE Transactions on Audio, Speech and Language Processing, 15(3), 1066\u20131074.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9875_CR21","doi-asserted-by":"publisher","unstructured":"Wang, K., Soong, F., & Xie, L. (2019). A pitch-aware approach to single-channel speech separation. In ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 296\u2013300). IEEE. Brighton, United Kingdom. https:\/\/doi.org\/10.1109\/ICASSP.2019.8683138.","DOI":"10.1109\/ICASSP.2019.8683138"},{"issue":"6","key":"9875_CR22","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1109\/TASL.2009.2016230","volume":"17","author":"B Yegnanarayana","year":"2009","unstructured":"Yegnanarayana, B., Swamy, R. K., & Murty, K. S. R. (2009). Determining mixing parameters from multispeaker data using speech-specific information. IEEE Transactions on Audio, Speech, and Language Processing, 17(6), 1196\u20131207.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"5","key":"9875_CR23","doi-asserted-by":"publisher","first-page":"967","DOI":"10.1109\/TASLP.2016.2536478","volume":"24","author":"XL Zhang","year":"2016","unstructured":"Zhang, X. L., & Wang, D. (2016). A deep ensemble learning method for monaural speech separation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 24(5), 967\u2013977.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09875-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09875-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09875-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T18:34:47Z","timestamp":1725561287000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09875-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,3]]},"references-count":22,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["9875"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09875-3","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2021,8,3]]},"assertion":[{"value":"8 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}