{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T22:40:05Z","timestamp":1748990405291,"version":"3.41.0"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319405414"},{"type":"electronic","value":"9783319405421"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-40542-1_64","type":"book-chapter","created":{"date-parts":[[2016,6,22]],"date-time":"2016-06-22T19:09:37Z","timestamp":1466622577000},"page":"392-400","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Speech Activity Detection and Speaker Localization Based on Distributed Microphones"],"prefix":"10.1007","author":[{"given":"Yi","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiasong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,6,22]]},"reference":[{"key":"64_CR1","doi-asserted-by":"crossref","unstructured":"Ward, D.B., Williamson, R.C.: Particle filter beamforming for acoustic source location in a reverberant environment. In: Proceedings of IEEE International Conference on Acoustic Speech Signal Processing (ICASSP), Orlando, USA, pp. II1777\u2013II1780, 13\u201317 May 2002","DOI":"10.1109\/ICASSP.2002.1006108"},{"key":"64_CR2","volume-title":"Microphone Array Signal Processing","author":"J Benesty","year":"2008","unstructured":"Benesty, J., Chen, J., Huang, Y.: Microphone Array Signal Processing. Springer, Berlin Heidelberg (2008)"},{"key":"64_CR3","unstructured":"Liu, Z.: Sound source separation with distributed microphone arrays in the presence of clock synchronization errors. In: 2008 International Workshop for Acoustic Echo and Noise Control (IWAENC 2008), Seattle, USA, 14\u201317 September 2008"},{"key":"64_CR4","unstructured":"Huijbregts, M., Leeuwen, D., Hain, T.: The AMI RT09s Speaker Diarization System. http:\/\/www.itl.nist.gov\/iad\/mig\/tests\/rt\/2009\/workshop\/ami-diarization.pdf"},{"key":"64_CR5","doi-asserted-by":"crossref","unstructured":"Jia, Y., Luo, Y., Lin, Y., Kozintsev, I.: Distributed microphone arrays for digital home and office. In: 2006 Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), Toulouse, France, vol. 5, pp. 1065\u20131068, 14\u201319 May 2006","DOI":"10.1109\/ICASSP.2006.1661463"},{"key":"64_CR6","unstructured":"Miro, X.A.: Robust speaker diarization for meetings. Ph.D. thesis of Universitat Politecnica de Catalunya, Spain (2006)"},{"issue":"12","key":"64_CR7","doi-asserted-by":"publisher","first-page":"2238","DOI":"10.1109\/TASLP.2015.2476762","volume":"23","author":"IC Yoo","year":"2015","unstructured":"Yoo, I.C., Lim, H., Yook, D.: Formant-based robust voice activity detection. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(12), 2238\u20132245 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"1","key":"64_CR8","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/0167-6393(89)90067-8","volume":"8","author":"MH Savoji","year":"1989","unstructured":"Savoji, M.H.: A robust algorithm for accurate endpointing of speech. Speech Commun. 8(1), 45\u201360 (1989)","journal-title":"Speech Commun."},{"key":"64_CR9","unstructured":"Khoa, P.C.: Noise robust voice activity detection. Master thesis of Nanyang Technological University, Singapore (2012)"},{"key":"64_CR10","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1007\/978-3-319-07857-1_97","volume-title":"HCI International 2014 \u2013 Posters\u2019 Extended Abstracts","author":"Y Yang","year":"2014","unstructured":"Yang, Y., Liu, J.: Exploring the large-scale TDOA feature space for speaker diarization. In: Stephanidis, C. (ed.) HCI 2014, Part I. CCIS, vol. 434, pp. 551\u2013556. Springer, Heidelberg (2014)"},{"issue":"1","key":"64_CR11","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"G Dahl","year":"2012","unstructured":"Dahl, G., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30\u201342 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"8","key":"64_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"64_CR13","doi-asserted-by":"crossref","unstructured":"Eyben, F., Weninger, F., Squartini, S., Schuller, B.: Real-life voice activity detection with LSTM recurrent neural networks and an application to hollywood movies. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), Vancouver, Canada, pp. 483\u2013487, 26\u201331 May 2013","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"64_CR14","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), Vancouver, Canada, pp. 6645\u20136649, 26\u201331 May 2013","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"64_CR15","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A.W., Beaufays, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014), Singapore, pp. 338\u2013342, 14\u201318 September 2014","DOI":"10.21437\/Interspeech.2014-80"},{"key":"64_CR16","unstructured":"Rich Transcription Evaluation Project. http:\/\/www.itl.nist.gov\/iad\/mig\/tests\/rt . Accessed 10 Mar 2016"}],"container-title":["Communications in Computer and Information Science","HCI International 2016 \u2013 Posters' Extended Abstracts"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-40542-1_64","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T22:27:04Z","timestamp":1748989624000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-40542-1_64"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319405414","9783319405421"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-40542-1_64","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"22 June 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}