{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T01:23:32Z","timestamp":1761701012863,"version":"build-2065373602"},"reference-count":20,"publisher":"Institution of Engineering and Technology (IET)","issue":"8","license":[{"start":{"date-parts":[[2013,10,1]],"date-time":"2013-10-01T00:00:00Z","timestamp":1380585600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IET Signal Processing"],"published-print":{"date-parts":[[2013,10]]},"abstract":"<jats:p>In this study, a novel technique that recovers the temporal structure of speech power spectrum is proposed. The histogram of average speech log power spectrum shows that the contamination of noise leads to the shift of noise peak, which in return degrades the performance of speech recognition systems. A two\u2010step scheme is proposed to weaken the noise effects by first reducing the noise variance and then shifting the noise mean. The proposed algorithm consists of two parts, two\u2010dimensional smoothing and controlled noise subtraction, which leads to the name SNS. The proposed algorithm manages to solve the speech probability distribution function discontinuity problem caused by traditional spectral subtraction series algorithms. In contrast to the clean speech estimation methods, the proposed algorithm does not need a prior speech\/noise statistical model, which makes it simple but effective. The effectiveness of the proposed filter is tested using the AURORA2 database. Very promising results are obtained, 88.59% for noisy speech (average from signal\u2010to\u2010noise ratio 0\u201320\u00a0dB). Comparison is made against eight state\u2010of\u2010the\u2010art speech recognition algorithms. Overall the proposed algorithm produces significant improvements over the comparison targets.<\/jats:p>","DOI":"10.1049\/iet-spr.2012.0357","type":"journal-article","created":{"date-parts":[[2013,8,29]],"date-time":"2013-08-29T16:13:44Z","timestamp":1377792824000},"page":"684-692","source":"Crossref","is-referenced-by-count":3,"title":["Robust speech recognition by using spectral subtraction with noise peak shifting"],"prefix":"10.1049","volume":"7","author":[{"given":"Peng","family":"Dai","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore 639798"}]},{"given":"Ing Yann","family":"Soon","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore 639798"}]}],"member":"265","published-online":{"date-parts":[[2013,10]]},"reference":[{"volume-title":"Fundamentals of speech recognition","year":"1993","author":"Rabiner L.","key":"e_1_2_6_2_2"},{"volume-title":"Speech and audio signal processing \u2013 processing and perception of speech and music","year":"2000","author":"Gold B.","key":"e_1_2_6_3_2"},{"key":"e_1_2_6_4_2","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2008.0211"},{"key":"e_1_2_6_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"e_1_2_6_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"e_1_2_6_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860851"},{"key":"e_1_2_6_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.822627"},{"key":"e_1_2_6_9_2","doi-asserted-by":"crossref","unstructured":"Droppo J. Acero A. Deng L.: \u2018Evaluation of the SPLICE algorithm on the Aurora 2 database\u2019.Proc. Eurospeech Conf. Int. Speech Communication Association Aalbodk Denmark September2001","DOI":"10.21437\/Eurospeech.2001-77"},{"key":"e_1_2_6_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2002082"},{"key":"e_1_2_6_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876717"},{"key":"e_1_2_6_12_2","unstructured":"European Telecommunications Standards Institute (ETSI) ETSI ES 202 050 V1.1.5 2007"},{"key":"e_1_2_6_13_2","doi-asserted-by":"crossref","unstructured":"Xu H. Tan Z.\u2010H. Salsgaard P. Lindberg B.: \u2018Spectral subtraction with full\u2010wave rectification and likelihood controlled instantaneous noise estimation for robust speech recognition\u2019.Proc. Int. Conf. Speech and Language Processing 2004","DOI":"10.21437\/Interspeech.2004-635"},{"key":"e_1_2_6_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/97.988717"},{"key":"e_1_2_6_15_2","doi-asserted-by":"crossref","unstructured":"Hirsch H. Pearce D.: \u2018The Aurora experimental framework for the performance evaluations of speech recognition system under noisy conditions\u2019.Proc. ISCA ITRW ASR 2000","DOI":"10.21437\/ICSLP.2000-743"},{"volume-title":"htkbook3.4","year":"2006","author":"Young S.","key":"e_1_2_6_16_2"},{"key":"e_1_2_6_17_2","unstructured":"Brookes M. Voicebox Available athttp:\/\/www.ee.ic.ac.uk\/hp\/staff\/dmb\/voicebox\/voicebox.html"},{"key":"e_1_2_6_18_2","unstructured":"Martin R.: \u2018Spectral subtraction based on minimum statistics\u2019.Proc. European Signal Processing Conf. 1994 pp.1182\u20131185"},{"key":"e_1_2_6_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/89.928915"},{"key":"e_1_2_6_20_2","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2008.0128"},{"key":"e_1_2_6_21_2","unstructured":"https:\/\/sites.google.com\/site\/declanide\/sample\u2010code"}],"container-title":["IET Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/iet-spr.2012.0357","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/iet-spr.2012.0357","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/iet-spr.2012.0357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T21:24:32Z","timestamp":1761686672000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/iet-spr.2012.0357"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,10]]},"references-count":20,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2013,10]]}},"alternative-id":["10.1049\/iet-spr.2012.0357"],"URL":"https:\/\/doi.org\/10.1049\/iet-spr.2012.0357","archive":["Portico"],"relation":{},"ISSN":["1751-9675"],"issn-type":[{"type":"print","value":"1751-9675"}],"subject":[],"published":{"date-parts":[[2013,10]]}}}