{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T17:36:29Z","timestamp":1762623389704},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,1,9]],"date-time":"2012-01-09T00:00:00Z","timestamp":1326067200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2012,12]]},"DOI":"10.1186\/1687-4722-2012-1","type":"journal-article","created":{"date-parts":[[2012,1,10]],"date-time":"2012-01-10T07:21:27Z","timestamp":1326180087000},"source":"Crossref","is-referenced-by-count":14,"title":["A novel voice activity detection based on phoneme recognition using statistical model"],"prefix":"10.1186","volume":"2012","author":[{"given":"Xulei","family":"Bao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,1,9]]},"reference":[{"issue":"7","key":"49_CR1","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MCOM.2004.1316528","volume":"42","author":"JH James","year":"2004","unstructured":"James JH, Chen B, Garrison L: Implementing VoIP: a voice transmission performance progress report. IEEE Commun Mag 2004, 42(7):36-41.","journal-title":"IEEE Commun Mag"},{"issue":"1","key":"49_CR2","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/MCOM.2008.4427240","volume":"46","author":"C Wang","year":"2008","unstructured":"Wang C, Sohraby K, Jana R, Lusheng J, Daneshmand M: Voice communications over ZigBee networks. IEEE Commun Mag 2008, 46(1):121-127.","journal-title":"IEEE Commun Mag"},{"issue":"1","key":"49_CR3","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1109\/TASL.2007.910790","volume":"16","author":"J Chien","year":"2008","unstructured":"Chien J, Ting C: Factor analyzed subspace modeling and selection. IEEE Trans Audio, Speech and Lang Process 2008, 16(1):239-248.","journal-title":"IEEE Trans Audio, Speech and Lang Process"},{"issue":"4","key":"49_CR4","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1109\/TSMCB.2007.895365","volume":"37","author":"Y Shao","year":"2007","unstructured":"Shao Y, Chang C: A generalized time-frequency subtraction method for robust speech enhancement based on wavelet filter banks modeling of human auditory system. IEEE Trans Systems, Man, and Cybernetic 2007, 37(4):877-889.","journal-title":"IEEE Trans Systems, Man, and Cybernetic"},{"issue":"8","key":"49_CR5","doi-asserted-by":"publisher","first-page":"2177","DOI":"10.1109\/TASL.2007.903937","volume":"15","author":"J Ramirez","year":"2007","unstructured":"Ramirez J, Segura JC, Gorriz JM, Garcia L: Improved voice activity detection using contextual multiple hypothesis testing for robust speech recognition. IEEE Trans Audio, Speech and Lang Process 2007, 15(8):2177-2189.","journal-title":"IEEE Trans Audio, Speech and Lang Process"},{"key":"49_CR6","first-page":"5333","volume-title":"Proceedings of the IEEE International Conference on Intelligent Robots and Systems","author":"S Yamamoto","year":"2006","unstructured":"Yamamoto S, Nakadai K, Nakano M, et al.: Real-time robot audition system that recognizes simultaneous speech in the real world. Proceedings of the IEEE International Conference on Intelligent Robots and Systems 2006, 5333-5338."},{"key":"49_CR7","first-page":"4441","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","author":"M Fujimoto","year":"2008","unstructured":"Fujimoto M, Ihizuka K, Nakatani T: A voice activity detection based on the adaptive integration of multiple speech features and signal decision scheme. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing 2008, 4441-4444."},{"issue":"6","key":"49_CR8","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/TASL.2006.872625","volume":"14","author":"G Evanglelopulos","year":"2006","unstructured":"Evanglelopulos G, Maragos P: Multiband modulation energy tracking for noisy speech detection. IEEE Trans Audio, Speech and Lang Process 2006, 14(6):2024-2038.","journal-title":"IEEE Trans Audio, Speech and Lang Process"},{"key":"49_CR9","first-page":"557","volume":"1","author":"J Padrell","year":"2005","unstructured":"Padrell J, Macho D, Nadeu C: Robust speech activity detection using LDA applied to FF parameters. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing 2005, 1: 557-560.","journal-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing"},{"key":"49_CR10","first-page":"407","volume-title":"Telecommunication Networks and Applications Conference","author":"M Asgari","year":"2008","unstructured":"Asgari M, Sayadian A, Frahadloo M, Mehrizi EA: Voice Activity Detection Using Entropy in Spectrum Domain. Telecommunication Networks and Applications Conference 2008, 407-410."},{"key":"49_CR11","first-page":"4482","volume-title":"Proceeding of the IEEE International Conference on Acoustics Speech and Signal Processing","author":"T Fukuda","year":"2010","unstructured":"Fukuda T, Ichikawa O, Nishimura M: Improved voice activity detection using static harmonic features. Proceeding of the IEEE International Conference on Acoustics Speech and Signal Processing 2010, 4482-4485."},{"issue":"5","key":"49_CR12","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1109\/TSA.2005.851955","volume":"13","author":"K Li","year":"2005","unstructured":"Li K, Swamy MNS, Ahmad OM: An improved voice activity detection using higher order statistics. IEEE Trans Speech and Audio Process 2005, 13(5):965-974.","journal-title":"IEEE Trans Speech and Audio Process"},{"issue":"1","key":"49_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/97.736233","volume":"16","author":"J Sohn","year":"1999","unstructured":"Sohn J, Kim NS, Sung W: A statistical model-based voice activity detection. IEEE Signal Process Lett 1999, 16(1):1-3.","journal-title":"IEEE Signal Process Lett"},{"key":"49_CR14","first-page":"737","volume":"2","author":"YD Cho","year":"2001","unstructured":"Cho YD, Al-Naimi K, Kondoz A: Improved voice activity detectionbased on a Smoothed statistical likelihood ratio. Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing 2001, 2: 737-740.","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing"},{"issue":"8","key":"49_CR15","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1109\/TASL.2008.2004293","volume":"16","author":"JM Gorriz","year":"2008","unstructured":"Gorriz JM, Ramirez J, Lang EW, Puntonet CG: Jointly Gaussian PDF-Based Likelihood Ratio Test for Voice Activity Detection. IEEE Trans On Audio, Speech and Lang Process 2008, 16(8):1565-1578.","journal-title":"IEEE Trans On Audio, Speech and Lang Process"},{"key":"49_CR16","first-page":"797","volume":"4","author":"M Fujimoto","year":"2007","unstructured":"Fujimoto M, Ishizuka K, Kato H: Noise Robust Voice Activity Detection based on Statistical Model and Parallel Non-linear Kalman Filtering. Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing 2007, 4: 797-800.","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing"},{"issue":"1","key":"49_CR17","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/97.988717","volume":"9","author":"I Cohen","year":"2002","unstructured":"Cohen I, Berdugo B: Noise estimation based by minima controlled recursive averaging for robust speech enhancement. IEEE Signal Process Lett 2002, 9(1):12-15. 10.1109\/97.988717","journal-title":"IEEE Signal Process Lett"},{"issue":"1","key":"49_CR18","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.specom.2009.08.003","volume":"52","author":"K Ishizuka","year":"2010","unstructured":"Ishizuka K, Nakatni T, Fujimoto M, Miyazaki N: Noise robust voice activity detection based on periodic to aperiodic component ratio. Speech Commun 2010, 52(1):41-60. 10.1016\/j.specom.2009.08.003","journal-title":"Speech Commun"},{"issue":"3","key":"49_CR19","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1109\/89.905996","volume":"9","author":"E Nemer","year":"2001","unstructured":"Nemer E, Goubran R, Mahmoud S: Robust voice activity detection using higher-order statistics in the LPC residual domain. IEEE Trans Speech Audio Process 2001, 9(3):217-231. 10.1109\/89.905996","journal-title":"IEEE Trans Speech Audio Process"},{"key":"49_CR20","unstructured":"Young S, Kershaw D, Odell J, Ollason D, Valtchev V, Woodland P: The HTK Book. Available from \n                    http:\/\/htk.eng.cam.ac.uk\/docs\/docs.shtml"},{"key":"49_CR21","first-page":"894","volume-title":"roceeding of the IEEE International Conference on Multimedia and Expo","author":"HH Xu","year":"2009","unstructured":"Xu HH, Zhu J, Wu GY: An efficient multistage ROVER for automatic speech recognition. roceeding of the IEEE International Conference on Multimedia and Expo 2009, 894-897."},{"key":"49_CR22","first-page":"4466","volume-title":"Proceeding of the IEEE International Conference on Acoustics Speech and Signal Processing","author":"LN Tan","year":"2010","unstructured":"Tan LN, Borgstrom BJ, Alwan A: Voice activity detection using harmonic frequency components in likelihood ratio test. Proceeding of the IEEE International Conference on Acoustics Speech and Signal Processing 2010, 4466-4469."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-4722-2012-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2012-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2012-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,22]],"date-time":"2019-01-22T01:56:38Z","timestamp":1548122198000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-4722-2012-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,1,9]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2012,12]]}},"alternative-id":["49"],"URL":"https:\/\/doi.org\/10.1186\/1687-4722-2012-1","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,1,9]]},"article-number":"1"}}