{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:07:02Z","timestamp":1743145622919,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"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_19","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:24:55Z","timestamp":1732191895000},"page":"250-263","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integration of\u00a0Short-Term and\u00a0Long-Term Harmonic Peaks in\u00a0a\u00a0Two-Level Discriminative Weight Training Framework for\u00a0Voice Activity Detection"],"prefix":"10.1007","author":[{"given":"YingWei","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Benyassine, A., Shlomot, E., Su, H.Y., Massaloux, D., Lamblin, C., Petit, J.P.: ITU-T recommendation G.729 annex B: a silence compression scheme for use with G.729 optimized for V.70 digital simultaneous voice and data applications. IEEE Commun. Mag. 35(9), 64\u201373 (1997)","DOI":"10.1109\/35.620527"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Cho, Y.D., Al-Naimi, K., Kondoz, A.: Improved voice activity detection based on a smoothed statistical likelihood ratio. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol.\u00a02, pp. 737\u2013740. IEEE (2001)","DOI":"10.1109\/ICASSP.2001.941020"},{"issue":"10","key":"19_CR3","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1109\/97.957270","volume":"8","author":"YD Cho","year":"2001","unstructured":"Cho, Y.D., Kondoz, A.: Analysis and improvement of a statistical model-based voice activity detector. IEEE Sig. Process. Lett. 8(10), 276\u2013278 (2001)","journal-title":"IEEE Sig. Process. Lett."},{"issue":"6","key":"19_CR4","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","volume":"32","author":"Y Ephraim","year":"1984","unstructured":"Ephraim, Y., Malah, D.: Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator. IEEE Trans. Acoust. Speech Sig. Process. 32(6), 1109\u20131121 (1984)","journal-title":"IEEE Trans. Acoust. Speech Sig. Process."},{"key":"19_CR5","unstructured":"ETSI: Voice activity detector (VAD) for adaptive multi-rate (AMR) speech traffic channels. Voice activity detector (VAD) for adaptive multi-rate (AMR) speech traffic channels (1999)"},{"key":"19_CR6","unstructured":"Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S.: Getting started with the DARPA TIMIT CD-ROM: an acoustic phonetic continuous speech database. Natl. Inst. Stan. Technol. 107, 16 (1988)"},{"key":"19_CR7","unstructured":"Hirsch, H.G., Pearce, D.: The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: ASR2000-Automatic Speech Recognition: Challenges for the New Millenium ISCA Tutorial and Research Workshop (ITRW) (2000)"},{"key":"19_CR8","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1109\/LSP.2007.913595","volume":"15","author":"SI Kang","year":"2008","unstructured":"Kang, S.I., Jo, Q.H., Chang, J.H.: Discriminative weight training for a statistical model-based voice activity detection. IEEE Sig. Process. Lett. 15, 170\u2013173 (2008)","journal-title":"IEEE Sig. Process. Lett."},{"issue":"1","key":"19_CR9","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/j.csl.2013.07.003","volume":"28","author":"MW Mak","year":"2014","unstructured":"Mak, M.W., Yu, H.B.: A study of voice activity detection techniques for NIST speaker recognition evaluations. Comput. Speech Lang. 28(1), 295\u2013313 (2014)","journal-title":"Comput. Speech Lang."},{"issue":"10","key":"19_CR10","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1109\/LSP.2005.855551","volume":"12","author":"J Ram\u00edrez","year":"2005","unstructured":"Ram\u00edrez, J., Segura, J.C., Ben\u00edtez, C., Garc\u00eda, L., Rubio, A.: Statistical voice activity detection using a multiple observation likelihood ratio test. IEEE Sig. Process. Lett. 12(10), 689\u2013692 (2005)","journal-title":"IEEE Sig. Process. Lett."},{"issue":"6","key":"19_CR11","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1109\/TSA.2005.853212","volume":"13","author":"J Ram\u00edrez","year":"2005","unstructured":"Ram\u00edrez, J., Segura, J.C., Ben\u00edtez, C., De la Torre, A., Rubio, A.: An effective subband OSF-based VAD with noise reduction for robust speech recognition. IEEE Trans. Speech Audio Process. 13(6), 1119\u20131129 (2005)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"1","key":"19_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/97.736233","volume":"6","author":"J Sohn","year":"1999","unstructured":"Sohn, J., Kim, N.S., Sung, W.: A statistical model-based voice activity detection. IEEE Sig. Process. Lett. 6(1), 1\u20133 (1999)","journal-title":"IEEE Sig. Process. Lett."},{"issue":"8","key":"19_CR13","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1109\/LSP.2012.2204978","volume":"19","author":"Y Suh","year":"2012","unstructured":"Suh, Y., Kim, H.: Multiple acoustic model-based discriminative likelihood ratio weighting for voice activity detection. IEEE Sig. Process. Lett. 19(8), 507\u2013510 (2012)","journal-title":"IEEE Sig. Process. Lett."},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Svirsky, J., Lindenbaum, O.: SG-VAD: stochastic gates based speech activity detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096938"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Tan, L.N., Borgstrom, B.J., Alwan, A.: Voice activity detection using harmonic frequency components in likelihood ratio test. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4466\u20134469. IEEE (2010)","DOI":"10.1109\/ICASSP.2010.5495611"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Tu, M., Xie, X., Jiao, Y.: Towards improving statistical model based voice activity detection. In: Interspeech (2014)","DOI":"10.21437\/Interspeech.2014-370"},{"key":"19_CR17","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"},{"issue":"11","key":"19_CR18","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1109\/LSP.2010.2066561","volume":"17","author":"T Yu","year":"2010","unstructured":"Yu, T., Hansen, J.H.: Discriminative training for multiple observation likelihood ratio based voice activity detection. IEEE Sig. Process. Lett. 17(11), 897\u2013900 (2010)","journal-title":"IEEE Sig. Process. Lett."}],"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_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T15:07:49Z","timestamp":1736348869000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78014-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031780134","9783031780141"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78014-1_19","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"}}]}}