{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,4]],"date-time":"2024-07-04T12:40:49Z","timestamp":1720096849127},"reference-count":22,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2016,7,1]],"date-time":"2016-07-01T00:00:00Z","timestamp":1467331200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100004541","name":"Ministry of Human Resource Development","doi-asserted-by":"publisher","award":["IIT\/SRIC\/SIT\/AVS\/2013-14\/209"],"id":[{"id":"10.13039\/501100004541","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2016,7]]},"DOI":"10.1016\/j.specom.2016.01.008","type":"journal-article","created":{"date-parts":[[2016,3,19]],"date-time":"2016-03-19T12:35:28Z","timestamp":1458390928000},"page":"90-103","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":12,"special_numbering":"C","title":["Voice\/non-voice detection using phase of zero frequency filtered speech signal"],"prefix":"10.1016","volume":"81","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-0686-4331","authenticated-orcid":false,"given":"S.B.","family":"Sunil Kumar","sequence":"first","affiliation":[]},{"given":"K.","family":"Sreenivasa Rao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.specom.2016.01.008_bib0001","series-title":"Proceedings of the Fifteenth Annual Conference of the International Speech Communication Association","article-title":"Noise spectrum estimation using Gaussian mixture model-based speech presence probability for robust speech recognition","author":"Alam","year":"2014"},{"key":"10.1016\/j.specom.2016.01.008_bib0002","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/TASSP.1976.1162800","article-title":"A pattern recognition approach to voiced-unvoiced-silence classification with applications to speech recognition","volume":"24","author":"Atal","year":"1976","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/j.specom.2016.01.008_bib0003","series-title":"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing","first-page":"648","article-title":"A novel spectral subtraction scheme for robust speech recognition: spectral subtraction using spectral harmonics of speech","volume":"1","author":"Beh","year":"2003"},{"key":"10.1016\/j.specom.2016.01.008_bib0004","series-title":"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing","first-page":"737","article-title":"Improved voice activity detection based on a smoothed statistical likelihood ratio","volume":"2","author":"Cho","year":"2001"},{"key":"10.1016\/j.specom.2016.01.008_bib0005","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1109\/TSA.2005.855842","article-title":"Statistical voice activity detection using low-variance spectrum estimation and an adaptive threshold","volume":"14","author":"Davis","year":"2006","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2016.01.008_bib0006","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1109\/LSP.2009.2038507","article-title":"Voiced\/nonvoiced detection based on robustness of voiced epochs","volume":"17","author":"Dhananjaya","year":"2010","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.specom.2016.01.008_bib0007","series-title":"Proceedings of Interspeech","first-page":"1973","article-title":"Joint robust voicing detection and pitch estimation based on residual harmonics","author":"Drugman","year":"2011"},{"key":"10.1016\/j.specom.2016.01.008_bib0008","series-title":"Digital Cellular Telecommunications System (Phase 2+)","article-title":"Adaptive Multi-Rate (AMR) speech; ANSI-C code for AMR speech codec","author":"ETSI","year":"1998"},{"key":"10.1016\/j.specom.2016.01.008_bib0009","series-title":"Digital Cellular Telecommunications System (Phase 2+)","article-title":"Voice Activity Detector (VAD) for Adaptive Multi-Rate (AMR) speech traffic channels; general description","author":"ETSI","year":"1999"},{"key":"10.1016\/j.specom.2016.01.008_bib0010","series-title":"Signal Theory","author":"Franks","year":"1969"},{"key":"10.1016\/j.specom.2016.01.008_bib0011","series-title":"Proceedings of International Conference on Acoustics, Speech, and Signal Processing","first-page":"369","article-title":"The voice activity detector for the Pan-European digital cellular mobile telephone service","volume":"1","author":"Freeman","year":"1989"},{"key":"10.1016\/j.specom.2016.01.008_bib0012","series-title":"Advances in Speech Signal Processing","first-page":"3","article-title":"Pitch and voicing determination","author":"Hess","year":"1992"},{"key":"10.1016\/j.specom.2016.01.008_bib0013","series-title":"Coding of Speech at 8 kbit\/s Using Conjugate Structure Algebraic Code \u2013 Excited Linear Prediction Annex B: A Silence Compression Scheme for G729 Optimized for Terminals Conforming to Recommend V70","author":"ITU","year":"1996"},{"key":"10.1016\/j.specom.2016.01.008_bib0014","series-title":"Coding of Speech at 8\u00a0kbit\/s Using Conjugate Structure Algebraic Code \u2013 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"},{"key":"10.1016\/j.specom.2016.01.008_bib0015","series-title":"Proceedings of the Fifth ISCA Workshop on Speech Synthesis, Pittsburgh, PA","first-page":"223","article-title":"The CMU Arctic speech databases","author":"Kominek","year":"2004"},{"key":"10.1016\/j.specom.2016.01.008_bib0016","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/0165-1684(80)90079-1","article-title":"Instantaneous envelope and phase extraction from real signals: theory, implementation, and an application to EEG analysis","volume":"2","author":"Ktonas","year":"1980","journal-title":"Signal Process."},{"key":"10.1016\/j.specom.2016.01.008_bib0017","first-page":"1602","article-title":"Epoch extraction from speech signals","volume":"16","author":"Murty","year":"2008","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/j.specom.2016.01.008_bib0018","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1109\/LSP.2009.2016829","article-title":"Characterization of glottal activity from speech signals","volume":"16","author":"Murty","year":"2009","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.specom.2016.01.008_bib0019","series-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"157","article-title":"Speech enhancement using harmonic regeneration","author":"Plapous","year":"2005"},{"key":"10.1016\/j.specom.2016.01.008_bib0020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/97.736233","article-title":"A statistical model-based voice activity detection","volume":"6","author":"Sohn","year":"1999","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.specom.2016.01.008_bib0021","series-title":"Proceedings of IEEE International Conference on Acoustics Speech and Signal Processing","first-page":"4466","article-title":"Voice activity detection using harmonic frequency components in likelihood ratio test","author":"Tan","year":"2010"},{"key":"10.1016\/j.specom.2016.01.008_bib0022","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","article-title":"Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems","volume":"12","author":"Varga","year":"1993","journal-title":"Speech Commun."}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639316000315?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639316000315?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2018,9,14]],"date-time":"2018-09-14T06:52:33Z","timestamp":1536907953000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639316000315"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7]]},"references-count":22,"alternative-id":["S0167639316000315"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2016.01.008","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2016,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Voice\/non-voice detection using phase of zero frequency filtered speech signal","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.specom.2016.01.008","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2016 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}