{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T16:41:58Z","timestamp":1762101718807,"version":"3.37.3"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,6,11]],"date-time":"2015-06-11T00:00:00Z","timestamp":1433980800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2015,6,11]],"date-time":"2015-06-11T00:00:00Z","timestamp":1433980800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["SCOPE: 131205001"],"award-info":[{"award-number":["SCOPE: 131205001"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["25240026"],"award-info":[{"award-number":["25240026"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004298","name":"Secom Science and Technology Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004298","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2016,2]]},"DOI":"10.1007\/s11265-015-1014-4","type":"journal-article","created":{"date-parts":[[2015,6,11]],"date-time":"2015-06-11T08:06:13Z","timestamp":1434009973000},"page":"163-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Robust Voice Activity Detection Based on Concept of Modulation Transfer Function in Noisy Reverberant Environments"],"prefix":"10.1007","volume":"82","author":[{"given":"Shota","family":"Morita","sequence":"first","affiliation":[]},{"given":"Masashi","family":"Unoki","sequence":"additional","affiliation":[]},{"given":"Xugang","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Masato","family":"Akagi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,6,11]]},"reference":[{"key":"1014_CR1","doi-asserted-by":"crossref","unstructured":"Ramirez, J., Gorriz, J.M., & Segura, J.C. (2007). Voice activity detection fundamentals and speech recognition system robustness. Robust Speech Recognition and Understanding, 1\u201322.","DOI":"10.5772\/4740"},{"issue":"5","key":"1014_CR2","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1250\/ast.30.363","volume":"30","author":"N Kitaoka","year":"2009","unstructured":"Kitaoka, N., Yamada, T., Tsuge, S., Miyajima, C., Yamamoto, K., Nishiura, T., Nakayama, M., Denda, Y., Fujimoto, M., Takiguchi, T., Tamura, S., Matsuda, S., Ogawa, T., Kuroiwa, S., Takeda, K., & Nakamura, S. (2009). CENSREC-1-C: An evaluation framework for voice activity detection under noisy environments. Acoustical Science and Technology, 30(5), 363\u2013371.","journal-title":"Acoustical Science and Technology"},{"key":"1014_CR3","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1109\/35.620527","volume":"35","author":"A Benyassine","year":"1997","unstructured":"Benyassine, A., Shlomot, E., Huan-yu, S., Massaloux, D., Lamblin, C., & Petit, J.P. (1997). 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 application. IEEE Communications Magazine, 35, 64\u201373.","journal-title":"IEEE Communications Magazine"},{"key":"1014_CR4","doi-asserted-by":"crossref","unstructured":"Lu, X., Unoki, M., Isotani, R., Kawai, H., & Nakamura, S. (2011). Adaptive regularization framework for robust voice activity detection. In Proceedings Interspeech2011 (pp. 2653\u20132653).","DOI":"10.21437\/Interspeech.2011-678"},{"key":"1014_CR5","unstructured":"ETSI EN 301 v7.1 (1999). Digital cellular telecommunications system; Voice Activity Detector (VAD) for Adaptive Multi-Rate (AMR) speech traffic channels."},{"key":"1014_CR6","doi-asserted-by":"crossref","unstructured":"Kanai, Y., Morita, S., & Unoki, M. (2013). Concurrent processing of voice activity detection and noise reduction using empirical mode decomposition and modulation spectrum analysis. In Proceedings Interspeech2013 (pp. 742\u2013746).","DOI":"10.21437\/Interspeech.2013-206"},{"key":"1014_CR7","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/JSTSP.2010.2069750","volume":"4","author":"T Fukuda","year":"2010","unstructured":"Fukuda, T., Ichikawa, O., & Nishimura, M. (2010). Long-term spectro-temporal and static harmonic features for voice activity detection. IEEE Journal of Selected Topics in Signal Processing, 4, 834\u2013844.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"1014_CR8","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1016\/j.compeleceng.2011.04.005","volume":"37","author":"\u00d3 Varela","year":"2011","unstructured":"Varela, \u00d3., San-Segundo, R., & Hern\u00e1ndez, L. (2011). Combining pulse-based features for rejecting far-field speech in a HMM-based voice activity detector. Computers and Electrical Engineering, 37, 589\u2013600.","journal-title":"Computers and Electrical Engineering"},{"key":"1014_CR9","unstructured":"Otsu, N. (1979). A threshold selection method from graylevel histograms. IEEE Transactions on Systems, Man, and Cybernetics, SMC-9, 61\u201366."},{"key":"1014_CR10","doi-asserted-by":"crossref","unstructured":"Unoki, M., Lu, X., Petrick, R., Morita, S., Akagi, M., & Hoffmann, R. (2011). Voice activity detection in MTF-based power envelope restoration. In Proceedings Interspeech2011 (pp. 2609\u20132612).","DOI":"10.21437\/Interspeech.2011-667"},{"issue":"4","key":"1014_CR11","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1250\/ast.25.232","volume":"25","author":"M Unoki","year":"2004","unstructured":"Unoki, M., Furukawa, M., Sakata, K., & Akagi, M. (2004). An improved method based on the MTF concept for restoring the power envelope from a reverberant signal. Acoustical Science and Technology, 25(4), 232\u2013242.","journal-title":"Acoustical Science and Technology"},{"issue":"4","key":"1014_CR12","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1250\/ast.25.243","volume":"25","author":"M Unoki","year":"2004","unstructured":"Unoki, M., Sakata, K., Furukawa, M., & Akagi, M. (2004). A speech dereverberation method based on the MTF concept in power envelope restoration. Acoustical Science and Technology, 25(4), 243\u2013254.","journal-title":"Acoustical Science and Technology"},{"key":"1014_CR13","first-page":"66","volume":"28","author":"T Houtgast","year":"1973","unstructured":"Houtgast, T., & Steeneken, H.J. (1973). The modulation transfer function in room acoustics as a predictor of speech intelligibility. Acustica, 28, 66\u201373.","journal-title":"Acustica"},{"key":"1014_CR14","unstructured":"Unoki, M., Yamasaki, Y., & Akagi, M. (2009). MTF-based power envelope restoration in noisy reverberant environments. In Proceedings EUSIPCO, (Vol. 2009 pp. 228\u2013232)."},{"key":"1014_CR15","doi-asserted-by":"crossref","unstructured":"Unoki, M., & Lu, X. (2012). Unified denoising and dereverberation method used in restoration of MTF-based power envelope. In Proceedings ISCSLP, (pp. 215\u2013219).","DOI":"10.1109\/ISCSLP.2012.6423499"},{"key":"1014_CR16","doi-asserted-by":"crossref","unstructured":"Schroeder, M.R. (1965). New method of measuring reverberation time. The Journal of the Acoustical Society of America, 489.","DOI":"10.1121\/1.1939454"},{"key":"1014_CR17","unstructured":"http:\/\/www.slp.cs.tut.ac.jp\/CENSREC\/en\/CENSREC\/AURORA-2J\/ (2012)."},{"key":"1014_CR18","unstructured":"Hirsch, H.G., & Pearce, D. (2000). The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In Proceedings ISCA ITRW ASR2000. Automatic speech recognition: challenges for the next millennium."},{"key":"1014_CR19","volume-title":"Sound library of architecture and environment","author":"Architectual Institute of Japan","year":"2004","unstructured":"Architectual Institute of Japan. (2004). Sound library of architecture and environment. Tokyo: Gihodo Shuppan Co, Ltd."},{"key":"1014_CR20","unstructured":"Kawai, K., Fujimoto, K., Iwase, T., Yasuoka, H., Sakuma, T., & Hidaka, Y. (2004). Development of a sound source database for environmental\/architectural acoustics: Introduction of SMILE 2004 (Sound Material in Living Environment 2004). In Proceedings ICA (pp. 1561\u20131564)."},{"issue":"13","key":"1014_CR21","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga, A., & Steeneken, H.J.M. (1993). 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 Communication, 12 (13), 247\u2013251.","journal-title":"Speech Communication"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1014-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-015-1014-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1014-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1014-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,12]],"date-time":"2022-05-12T13:24:20Z","timestamp":1652361860000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-015-1014-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,11]]},"references-count":21,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,2]]}},"alternative-id":["1014"],"URL":"https:\/\/doi.org\/10.1007\/s11265-015-1014-4","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"type":"print","value":"1939-8018"},{"type":"electronic","value":"1939-8115"}],"subject":[],"published":{"date-parts":[[2015,6,11]]},"assertion":[{"value":"15 November 2014","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2015","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2015","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2015","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}