{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:40:51Z","timestamp":1743025251310,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030821982"},{"type":"electronic","value":"9783030821999"}],"license":[{"start":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T00:00:00Z","timestamp":1628294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T00:00:00Z","timestamp":1628294400000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-82199-9_55","type":"book-chapter","created":{"date-parts":[[2021,11,10]],"date-time":"2021-11-10T09:02:45Z","timestamp":1636534965000},"page":"823-829","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Application of Adversarial Domain Adaptation to Voice Activity Detection"],"prefix":"10.1007","author":[{"given":"TaeSoo","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong Hwan","family":"Ko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,7]]},"reference":[{"key":"55_CR1","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. arXiv preprint arXiv:1406.2661 (2014)"},{"key":"55_CR2","doi-asserted-by":"crossref","unstructured":"Tzeng, E., et al.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167\u20137176 (2017)","DOI":"10.1109\/CVPR.2017.316"},{"key":"55_CR3","doi-asserted-by":"crossref","unstructured":"Kim, J., Kim, J., Lee, S., Park, J., Hahn, M.: Vowel based voice activity detection with LSTM recurrent neural network. In Proceedings of the 8th International Conference on Signal Processing Systems, pp. 134\u2013137 (November 2016)","DOI":"10.1145\/3015166.3015207"},{"key":"55_CR4","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, pp. 483\u2013487. IEEE (May 2013)","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"55_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, X. L., Wang, D.: Boosted deep neural networks and multi-resolution cochleagram features for voice activity detection. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)","DOI":"10.21437\/Interspeech.2014-367"},{"key":"55_CR6","doi-asserted-by":"crossref","unstructured":"Kim, J., Hahn, M.: Voice activity detection using an adaptive context attention model. IEEE Sig. Process. Lett. 25(8), 1181\u20131185 (2018)","DOI":"10.1109\/LSP.2018.2811740"},{"key":"55_CR7","doi-asserted-by":"crossref","unstructured":"Tong, S., Gu, H., Yu, K.: A comparative study of robustness of deep learning approaches for VAD. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5695\u20135699. IEEE (March 2016)","DOI":"10.1109\/ICASSP.2016.7472768"},{"key":"55_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, X.L., Wu, J.: Deep belief networks based voice activity detection. IEEE Trans. Audio, Speech, Lang. Process. 21(4), 697\u2013710 (2012)","DOI":"10.1109\/TASL.2012.2229986"},{"key":"55_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, X.-L.: Unsupervised domain adaptation for deep neural network based voice activity detection. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6864\u20136868. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854930"},{"key":"55_CR10","doi-asserted-by":"crossref","unstructured":"Lavechin, M., Gill, M. P., Bousbib, R., Bredin, H., Garcia-Perera, L.P.: End-to-end Domain-Adversarial Voice Activity Detection. arXiv preprint arXiv:1910.10655 (2019)","DOI":"10.21437\/Interspeech.2020-2285"},{"key":"55_CR11","doi-asserted-by":"crossref","unstructured":"Shahid, M., Beyan, C., Murino, V.: Voice activity detection by upper body motion analysis and unsupervised domain adaptation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00159"},{"key":"55_CR12","doi-asserted-by":"crossref","unstructured":"Varga, A., Steeneken, H.J.: Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12(3), 247\u2013251 (1993)","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"55_CR13","doi-asserted-by":"crossref","unstructured":"Zue, V., Seneff, S., Glass, J.: Speech database development at MIT: TIMIT and beyond. Speech Commun. 9(4), 351\u2013356 (1990)","DOI":"10.1016\/0167-6393(90)90010-7"},{"key":"55_CR14","unstructured":"Berthelot, D., Schumm, T., Metz, L.: Began: Boundary equilibrium generative adversarial networks. arXiv preprint arXiv:1703.10717 (2017)"},{"key":"55_CR15","doi-asserted-by":"crossref","unstructured":"Ishizuka, K., Nakatani, T., Fujimoto, M., Miyazaki, N.: Noise robust voice activity detection based on periodic to aperiodic component ratio. Speech Commun. 52(1), 41\u201360 (2010)","DOI":"10.1016\/j.specom.2009.08.003"},{"key":"55_CR16","unstructured":"SoSound-ideas.com, Generalseries6000combo (2012). https:\/\/www.sound-ideas.com\/Product\/51\/General-Series-6000-Combo"},{"key":"55_CR17","doi-asserted-by":"crossref","unstructured":"Hanley, J.A., McNeil, B.J.: The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1), 29\u201336 (1982)","DOI":"10.1148\/radiology.143.1.7063747"},{"key":"55_CR18","unstructured":"Hirsch, H.G.: Fant-filtering and noise adding tool. Niederrhein University of Applied Sciences (2005). http:\/\/dnt.kr.hsnr.de\/download.html"},{"key":"55_CR19","doi-asserted-by":"crossref","unstructured":"Ravanelli, M., Bengio, Y.: Speaker recognition from raw waveform with sincnet. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 1021\u20131028. IEEE (December 2018)","DOI":"10.1109\/SLT.2018.8639585"},{"key":"55_CR20","doi-asserted-by":"crossref","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Sig. Process. 45(11), 2673\u20132681 (1997)","DOI":"10.1109\/78.650093"}],"container-title":["Lecture Notes in Networks and Systems","Intelligent Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-82199-9_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,10]],"date-time":"2021-11-10T09:14:01Z","timestamp":1636535641000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-82199-9_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,7]]},"ISBN":["9783030821982","9783030821999"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-82199-9_55","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2021,8,7]]},"assertion":[{"value":"7 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IntelliSys","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Proceedings of SAI Intelligent Systems Conference","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"intellisys2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/saiconference.com\/IntelliSys","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}