{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:43:16Z","timestamp":1776879796024,"version":"3.51.2"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,7,16]],"date-time":"2013-07-16T00:00:00Z","timestamp":1373932800000},"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":[[2013,12]]},"DOI":"10.1186\/1687-4722-2013-21","type":"journal-article","created":{"date-parts":[[2013,7,16]],"date-time":"2013-07-16T22:14:12Z","timestamp":1374012852000},"source":"Crossref","is-referenced-by-count":53,"title":["Efficient voice activity detection algorithm using long-term spectral flatness measure"],"prefix":"10.1186","volume":"2013","author":[{"given":"Yanna","family":"Ma","sequence":"first","affiliation":[]},{"given":"Akinori","family":"Nishihara","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,7,16]]},"reference":[{"key":"87_CR1","first-page":"419","volume-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)","author":"K Itoh","year":"1997","unstructured":"Itoh K, Mizushima M: Environmental noise reduction based on speech\/non-speech identification for hearing aids. In IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). Piscataway: IEEE; 1997:419\u2013422."},{"key":"87_CR2","first-page":"369","volume-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)","author":"D Freeman","year":"1989","unstructured":"Freeman D, Cosier G, Southcott C, Boyd I: The voice activity detector for the Pan-European digital cellular mobile telephone service. In IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). Piscataway: IEEE; 1989:369\u2013372."},{"key":"87_CR3","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/HSCMA.2011.5942412","volume-title":"2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), Edinburgh,30 May\u20131 June 2011","author":"F Faubel","year":"2011","unstructured":"Faubel F, Georges M, Kumatani K, Bruhn A, Klakow D: Improving hands-free speech recognition in a car through audio-visual voice activity detection. In 2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), Edinburgh,30 May\u20131 June 2011. Piscataway: IEEE; 2011:70\u201375."},{"key":"87_CR4","doi-asserted-by":"crossref","first-page":"3096","DOI":"10.1109\/GLOCOM.2007.586","volume-title":"Global Telecommunications Conference (GLOBECOM \u201907), Washington DC, 26\u201330 November 2007","author":"W Syed","year":"2007","unstructured":"Syed W, Wu HC: Speech waveform compression using robust adaptive voice activity detection for nonstationary noise in multimedia communications. In Global Telecommunications Conference (GLOBECOM \u201907), Washington DC, 26\u201330 November 2007. Piscataway: IEEE; 2007:3096\u20133101."},{"key":"87_CR5","first-page":"196","volume-title":"3rd European Conference on Satellite Communications (ECSC-3), Manchester, 2\u20134 Nov 1993","author":"A Kondoz","year":"1993","unstructured":"Kondoz A, Evans B: A high quality voice coder with integrated echo canceller and voice activity detector for VSAT systems. In 3rd European Conference on Satellite Communications (ECSC-3), Manchester, 2\u20134 Nov 1993. Piscataway: IEEE; 1993:196\u2013200."},{"key":"87_CR6","first-page":"97","volume-title":"IEEE Workshop on Speech Coding For Telecommunications Proceeding","author":"A Benyassine","year":"1997","unstructured":"Benyassine A, Shlomot E, Su HY, Yuen E: A robust low complexity voice activity detection algorithm for speech communication systems. In IEEE Workshop on Speech Coding For Telecommunications Proceeding. Piscataway: IEEE; 1997:97\u201398."},{"issue":"2","key":"87_CR7","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1002\/j.1538-7305.1975.tb02840.x","volume":"54","author":"LR Rabiner","year":"1975","unstructured":"Rabiner LR, Sambur MR: An algorithm for determining the endpoints of isolated utterances. Bell Syst. Techn. J 1975,54(2):297\u2013315.","journal-title":"Bell Syst. Techn. J"},{"issue":"2","key":"87_CR8","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1109\/TSA.2005.855842","volume":"14","author":"A Davis","year":"2006","unstructured":"Davis A, Nordholm S, Togneri R: Statistical voice activity detection using low-variance spectrum estimation and an adaptive threshold. Audio, Speech, Lang. Proc. IEEE Trans 2006,14(2):412\u2013424.","journal-title":"Audio, Speech, Lang. Proc. IEEE Trans"},{"key":"87_CR9","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1109\/ETCS.2009.586","volume-title":"First International Workshop on Education Technology and Computer Science (ETCS \u201909)","author":"Z Shuyin","year":"2009","unstructured":"Shuyin Z, Ying G, Buhong W: Auto-correlation property of speech and its application in voice activity detection. In First International Workshop on Education Technology and Computer Science (ETCS \u201909). Piscataway: IEEE; 2009:265\u2013268."},{"issue":"2","key":"87_CR10","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/89.985548","volume":"10","author":"M Marzinzik","year":"2002","unstructured":"Marzinzik M, Kollmeier B: Speech pause detection for noise spectrum estimation by tracking power envelope dynamics. Speech and Audio Proc. IEEE Trans 2002,10(2):109\u2013118.","journal-title":"Speech and Audio Proc. IEEE Trans"},{"issue":"3","key":"87_CR11","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. Speech and Audio Proc. IEEE Trans 2001,9(3):217\u2013231.","journal-title":"Speech and Audio Proc. IEEE Trans"},{"issue":"3\u20134","key":"87_CR12","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.specom.2003.10.002","volume":"42","author":"J Ramirez","year":"2004","unstructured":"Ramirez J, Segura J, Benitez C, Torre A, Rubio A: Efficient voice activity detection algorithms using long-term speech information. Speech Commun 2004,42(3\u20134):271\u2013287.","journal-title":"Speech Commun"},{"key":"87_CR13","unstructured":"Lee B, Hasegawa-Johnson M: Minimum mean squared error a posteriori estimation of high variance vehicular noise. Proceedings of Biennial on DSP for In-Vehicle and Mobile Systems, Istanbul, 17\u201319 June 2007"},{"key":"87_CR14","volume-title":"Noise robust voice activity detection.","author":"PC Khoa","year":"2012","unstructured":"Khoa PC: Noise robust voice activity detection. Master\u2019s thesis, NangYang Technological University, 2012"},{"issue":"3","key":"87_CR15","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TASL.2010.2052803","volume":"19","author":"P Ghosh","year":"2011","unstructured":"Ghosh P, Tsiartas A, Narayanan S: Robust voice activity detection using long-term signal variability. Audio, Speech, and Lang. Proc. IEEE Trans 2011,19(3):600\u2013613.","journal-title":"Audio, Speech, and Lang. Proc. IEEE Trans"},{"issue":"23","key":"87_CR16","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1049\/el.2009.1977","volume":"45","author":"N Madhu","year":"2009","unstructured":"Madhu N: Note on measures for spectral flatness. Electron. Lett 2009,45(23):1195\u20131196.","journal-title":"Electron. Lett"},{"key":"87_CR17","volume-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus","author":"JS Garofolo","year":"1993","unstructured":"Garofolo JS, Lamel LF, Fisher WM, Fiscus JG, Pallett DS, Dahlgren NL, Zue V: TIMIT Acoustic-Phonetic Continuous Speech Corpus. Philadelphia: Linguistic Data Consortium; 1993."},{"key":"87_CR18","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.21437\/Eurospeech.2001-446","volume-title":"IEEE Proceedings of 7th European Conference on Speech Communication and Technology (EUROSPEECH\u20192001)","author":"P Renevey","year":"2001","unstructured":"Renevey P, Drygajlo A: Entropy based voice activity detection in very noisy conditions. In IEEE Proceedings of 7th European Conference on Speech Communication and Technology (EUROSPEECH\u20192001). Piscataway: IEEE; 2001:1887\u20131890."},{"key":"87_CR19","volume-title":"Statistical and Adaptive Signal Processing: Spectral Estimation, Signal Modeling, Adaptive Filtering, and Array Processing","author":"D Manolakis","year":"2005","unstructured":"Manolakis D, Ingle V, Kogon S: Statistical and Adaptive Signal Processing: Spectral Estimation, Signal Modeling, Adaptive Filtering, and Array Processing. Norwood: Artech House; 2005."},{"key":"87_CR20","doi-asserted-by":"crossref","DOI":"10.1201\/9781482264739","volume-title":"Engineering Noise Control: Theory and Practice","author":"D Bies","year":"2003","unstructured":"Bies D: Engineering Noise Control: Theory and Practice. New York: Taylor & Francis; 2003."},{"issue":"3","key":"87_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 HJ: 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 1993,12(3):247\u2013251.","journal-title":"Speech Commun"},{"key":"87_CR22","first-page":"530","volume-title":"Proceedings of the Seventh International Symposium on Computers and Communications (ISCC\u201902), Washington, DC","author":"RV Prasad","year":"2002","unstructured":"Prasad RV, Sangwan A, Jamadagni HS, Chiranth MC, Sah R, Gaurav V: Comparison of voice activity detection algorithms for VoIP. In Proceedings of the Seventh International Symposium on Computers and Communications (ISCC\u201902), Washington, DC. Piscataway: IEEE; 2002:530\u2013535."},{"key":"87_CR23","first-page":"1425","volume-title":"Proceedings of Acoustics, Speech, and Signal Processing (ICASSP \u201901)","author":"F Beritelli","year":"2001","unstructured":"Beritelli F, Casale S, Ruggeri G: Performance evaluation and comparison of ITU-T\/ETSI voice activity detectors. In Proceedings of Acoustics, Speech, and Signal Processing (ICASSP \u201901). Piscataway: IEEE; 2001:1425\u20131428."},{"key":"87_CR24","first-page":"807","volume-title":"5th International Conference on Signal Processing Proceedings (WCCC-ICSP 2000)","author":"F Beritelli","year":"2000","unstructured":"Beritelli F, Casale S, Ruggeri G: A psychoacoustic auditory model to evaluate the performance of a voice activity detector. In 5th International Conference on Signal Processing Proceedings (WCCC-ICSP 2000). Piscataway: IEEE; 2000:807\u2013810."},{"key":"87_CR25","volume-title":"Digital Cellular Telecommunications System (Phase 2+); Voice Activity Detector (VAD) for Adaptive Multi-Rate (AMR) Speech Traffic Channels; General Description","author":"ETSI","year":"1999","unstructured":"ETSI: Digital Cellular Telecommunications System (Phase 2+); Voice Activity Detector (VAD) for Adaptive Multi-Rate (AMR) Speech Traffic Channels; General Description. Valbonne: ETSI; 1999."},{"key":"87_CR26","volume-title":"Coding of Speech at 8 kbit\/s Using Conjugate Structure Algebraic Code - Excited Linear Prediction Annex B: A Silence Compression Scheme for G729 Optimized for Terminals Conforming to Recommend V70","author":"ITU","year":"1996","unstructured":"ITU: Coding of Speech at 8 kbit\/s Using Conjugate Structure Algebraic Code - Excited Linear Prediction Annex B: A Silence Compression Scheme for G729 Optimized for Terminals Conforming to Recommend V70. Geneva: International Telecommunication Union; 1996."},{"key":"87_CR27","volume-title":"Digital Cellular Telecommunications System (Phase 2+); Adaptive Multi-Rate (AMR) Speech; ANSI-C Code for AMR Speech Codec","author":"ETSI","year":"1998","unstructured":"ETSI: Digital Cellular Telecommunications System (Phase 2+); Adaptive Multi-Rate (AMR) Speech; ANSI-C Code for AMR Speech Codec. Valbonne: ETSI; 1998."},{"key":"87_CR28","volume-title":"Coding of Speech at 8 kbit\/s Using Conjugate Structure Algebraic Code - Excited Linear Prediction Annex I: Reference Fixed-Point Implementation for Integrating G729 CS-ACELP Speech Coding Main Body with Annexes B, D and E","author":"ITU","year":"2000","unstructured":"ITU: Coding of Speech at 8 kbit\/s Using Conjugate Structure Algebraic Code - Excited Linear Prediction Annex I: Reference Fixed-Point Implementation for Integrating G729 CS-ACELP Speech Coding Main Body with Annexes B, D and E. Geneva: International Telecommunication Union; 2000."}],"updated-by":[{"DOI":"10.1186\/s13636-015-0071-8","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2015,10,20]],"date-time":"2015-10-20T00:00:00Z","timestamp":1445299200000}}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-4722-2013-21\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2013-21.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2013-21.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T20:21:44Z","timestamp":1715718104000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-4722-2013-21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,7,16]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["87"],"URL":"https:\/\/doi.org\/10.1186\/1687-4722-2013-21","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,7,16]]},"article-number":"87"}}