{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T17:57:40Z","timestamp":1773511060903,"version":"3.50.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,1,20]],"date-time":"2017-01-20T00:00:00Z","timestamp":1484870400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41471303"],"award-info":[{"award-number":["41471303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Training project for outstanding young teachers of North China University of Technology, Special Research Foundation of North China University of Technology","award":["PXM2017_014212_000014"],"award-info":[{"award-number":["PXM2017_014212_000014"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Wireless Pers Commun"],"published-print":{"date-parts":[[2017,8]]},"DOI":"10.1007\/s11277-017-3958-0","type":"journal-article","created":{"date-parts":[[2017,1,20]],"date-time":"2017-01-20T15:34:19Z","timestamp":1484926459000},"page":"2073-2090","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["An Improved Endpoint Detection Algorithm Based on MFCC Cosine Value"],"prefix":"10.1007","volume":"95","author":[{"given":"Danyang","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,1,20]]},"reference":[{"issue":"2","key":"3958_CR1","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1109\/TCE.2006.1649683","volume":"52","author":"J Beh","year":"2006","unstructured":"Beh, J., Baran, R. H., & Ko, H. (2006). Dual channel based speech enhancement using novelty filter for robust speech recognition in automobile environment. IEEE Transactions on Consumer Electronics, 52(2), 583\u2013589.","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"3958_CR2","doi-asserted-by":"crossref","unstructured":"Beh, J., \u00a0& Ko, H. (2003). Spectral subtraction using spectral harmonics for robust speech recognition in car environments. In Computational science, vol. 2660 of lecture notes in computer science (pp. 1109\u20131116). Springer.","DOI":"10.1007\/3-540-44864-0_115"},{"issue":"5","key":"3958_CR3","first-page":"115","volume":"42","author":"J Zhang","year":"2015","unstructured":"Zhang, J., Zhang, D., & Cui, L. (2015). One speech endpoint detection with a robust adaptive threshold. Xi\u2019an University of Electronic Technology (10), 42(5), 115\u2013119.","journal-title":"Xi\u2019an University of Electronic Technology (10)"},{"issue":"3\u20134","key":"3958_CR4","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/0885-2308(87)90015-5","volume":"2","author":"JG Wilpon","year":"1987","unstructured":"Wilpon, J. G., & Rabiner, L. R. (1987). Application of hidden Markov models to automatic speech endpoint detection. Computer Speech & Language, 2(3\u20134), 321\u2013341.","journal-title":"Computer Speech & Language"},{"issue":"5","key":"3958_CR5","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1109\/TSA.2005.851909","volume":"13","author":"BF Wu","year":"2005","unstructured":"Wu, B.-F., & Wang, K.-C. (2005). Robust endpoint detection algorithm based on the adaptive band-partitioning spectral entropy in adverse environments. IEEE Transactions on Speech and Audio Processing, 13(5), 762\u2013774.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"3958_CR6","first-page":"2004","volume-title":"\u201cEf-ficient Likelihood Computation in Multi-Stream HMM Based Audio-Visual Speech Recognition\u201d, in Int","author":"E Marcheret","year":"2004","unstructured":"Marcheret, E., Chu, S., Goel, V., & Potamianos, G. (2004). \u201cEf-ficient Likelihood Computation in Multi-Stream HMM Based Audio-Visual Speech Recognition\u201d, in Int (p. 2004). Speech and Language Processing: Conf."},{"key":"3958_CR7","doi-asserted-by":"crossref","unstructured":"Povey, D., & Woodland, P. C. (2002). Minimum phone error and i-smoothing for improved discriminative training. In Proceedings of the ICASSP.","DOI":"10.1109\/ICASSP.2002.1005687"},{"key":"3958_CR8","doi-asserted-by":"crossref","unstructured":"Povey, D., Kingsbury, B., Mangu, L., Saon, G., Soltau, H., & Zweig, G. (2005). fMPE: Discriminatively trained features for speech recognition. In Proceedings of the ICASSP.","DOI":"10.1109\/ICASSP.2005.1415275"},{"key":"3958_CR9","doi-asserted-by":"crossref","unstructured":"Huang, J., & Povey, D. (2005). Discriminatively trained features using fMPE for multi-stream audio\u2013visual speech recognition. In Proceedings of the interspeech.","DOI":"10.21437\/Interspeech.2005-361"},{"key":"3958_CR10","doi-asserted-by":"crossref","unstructured":"Huang, J., & Visweswariah, K. (2009). Combined discriminative training for multi-stream HMM-based audio\u2013visual speech recognition. In Proceedings of the interspeech.","DOI":"10.21437\/Interspeech.2009-426"},{"key":"3958_CR11","doi-asserted-by":"crossref","unstructured":"Shen, J. L., Hung J. W., & Lee L. S. (1998). Robust entropy-based endpoint detection for speech recognition in noisy environments. In International conference on spoken language processing (pp. 232\u2013238), Sydney, Australia.","DOI":"10.21437\/ICSLP.1998-527"},{"issue":"25","key":"3958_CR12","doi-asserted-by":"crossref","first-page":"1869","DOI":"10.1049\/el:20031200","volume":"39","author":"CA Medina","year":"2008","unstructured":"Medina, C. A., & Alcaim, A. (2008). Wavelet denoising of speech using neural networks for threshold election. Electronics Letter, 39(25), 1869\u20131871.","journal-title":"Electronics Letter"},{"key":"3958_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.csl.2015.11.003","volume":"38","author":"I Hwanga","year":"2016","unstructured":"Hwanga, I., Parkb, H.-M., & Changa, J.-H. (2016). Ensemble of deep neural networks using acoustic environment classification for statistical model-based voice activity detection. Computer Speech & Language, 38, 1\u201312.","journal-title":"Computer Speech & Language"},{"key":"3958_CR14","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1002\/j.1538-7305.1984.tb00016.x","volume":"63","author":"JC Wilpon","year":"1984","unstructured":"Wilpon, J. C., Rabiner, L. R., & Martin, T. (1984). An improved word-detection algorithm for telephone-quality speech incorporating both syntactic and semantic constraints. AT&T Bell Laboratories Technical Journal, 63, 479\u2013498.","journal-title":"AT&T Bell Laboratories Technical Journal"},{"key":"3958_CR15","unstructured":"Chengalvarayan, R. (1999). Robust energy normalization using speech\/non-speech discriminator for German connected digit recognition. In: Proceedings of the Euro speech 99 (pp. 61\u201364), Budapest, Hungary."},{"key":"3958_CR16","doi-asserted-by":"crossref","unstructured":"Haigh, J. A., & Mason, J. S. (1993). Robust voice activity detection using cepstral features. In Proceedings of the IEEE TENCON (pp. 321\u2013324).","DOI":"10.1109\/TENCON.1993.327987"},{"key":"3958_CR17","first-page":"52","volume":"7","author":"R Zhang","year":"2005","unstructured":"Zhang, R., & Cui, H. (2005). Study endpoint detection algorithm based on short-term energy. Audio Engineering, 7, 52\u201354.","journal-title":"Audio Engineering"},{"issue":"5","key":"3958_CR18","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1109\/TSA.2005.851909","volume":"13","author":"B\u2013F Wu","year":"2005","unstructured":"Wu, B.\u2013F., & Wang, K.\u2013C. (2005). Robust endpoint detection algorithm based on the adaptive band-partitioning spectral entropy in adverse environments. IEEE Transactions on Speech and Audio Processing, 13(5), 762\u2013774.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"8","key":"3958_CR19","first-page":"2278","volume":"25","author":"H Liu","year":"2008","unstructured":"Liu, H., Li, X., Xu, B., & Jiang, N. (2008). The summary and outlook for speech signal endpoint detection. Computer Application sand Research (10), 25(8), 2278\u20132283.","journal-title":"Computer Application sand Research (10)"},{"key":"3958_CR20","doi-asserted-by":"crossref","unstructured":"Rabiner, L. R., & Sambur, M. R. (1977). Voiced-unvoiced-silence detection using the Itakura LPC distance measure. In Proceedings of the ICASSP (pp. 323\u2013326).","DOI":"10.1109\/ICASSP.1977.1170330"},{"key":"3958_CR21","unstructured":"Haign, J. A., & Mason, J. S. (1993). Robust voice activity detection using cepstral features. In Proceedings of the IEEE TEN-CON (pp. 321\u2013324)."},{"key":"3958_CR22","unstructured":"Chengalvarayan, R. (1999). Robust energy normalization using speech\/non-speech discriminator for German connected digit recognition. In Proceedings of the Euro speech (pp. 61\u201364)."},{"key":"3958_CR23","unstructured":"Voice activity detector (VAD) for adaptive multi-rate (AMR) speech traffic channels, ETSI EN 301 708 recommendation, ETSI, 1999."},{"key":"3958_CR24","unstructured":"Speech processing, transmission and quality aspects (STQ), distributed speech recognition; front-end feature extraction algorithm; compression algorithm, ETSI ES 202 050 recommendation, ETSI, 2002."},{"key":"3958_CR25","unstructured":"Yang, L. (2015). Voice endpoint detection based on MFCC distance. Information and Communication, 7, 31\u201332."},{"key":"3958_CR26","first-page":"1220","volume":"4","author":"H Han","year":"2014","unstructured":"Han, H., Wang, B., & Duan, S. (2014). Voice activity detection technology research and development. Computer Applications and Research, 4, 1220\u20131226.","journal-title":"Computer Applications and Research"},{"key":"3958_CR27","unstructured":"Shu, Q., & Li, Y. (2007). Speech endpoint detection based on MFCC. Communications Technology, 40(11), 374\u2013375."},{"key":"3958_CR28","unstructured":"Wang, H., Xu, Y., & Li, M. (2011). Study on the MFCC similarity-based voice activity detection algorithm. In 2nd International conference on artificial intelligence."},{"issue":"1","key":"3958_CR29","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.specom.2005.08.002","volume":"48","author":"M Kotta","year":"2006","unstructured":"Kotta, M., & Preen, R. (2006). Speech enhancement in non-stationary noise environments using noise properties. Speech Communication, 48(1), 96\u2013109.","journal-title":"Speech Communication"},{"key":"3958_CR30","unstructured":"Liu, J., Xu, Z., Zheng, Z., & Cheng, Q. (2005). DTW-based speech recognition and speaker recognition feature selection. Pattern Recognition and Artificial Intelligence, 18(1), 50\u201354."}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11277-017-3958-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-017-3958-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-017-3958-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T21:34:24Z","timestamp":1692653664000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11277-017-3958-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,20]]},"references-count":30,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,8]]}},"alternative-id":["3958"],"URL":"https:\/\/doi.org\/10.1007\/s11277-017-3958-0","relation":{},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"value":"0929-6212","type":"print"},{"value":"1572-834X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,1,20]]}}}