{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T15:58:56Z","timestamp":1762444736770,"version":"3.41.0"},"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2017,9,19]],"date-time":"2017-09-19T00:00:00Z","timestamp":1505779200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61503264"],"award-info":[{"award-number":["61503264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"DOI":"10.1371\/journal.pone.0184267","type":"journal-article","created":{"date-parts":[[2017,9,19]],"date-time":"2017-09-19T17:27:48Z","timestamp":1505842068000},"page":"e0184267","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Automatic initial and final segmentation in cleft palate speech of Mandarin speakers"],"prefix":"10.1371","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7168-2737","authenticated-orcid":true,"given":"Ling","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junpeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2017,9,19]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"154","DOI":"10.3758\/s13423-012-0326-7","article-title":"The syllable as the proximate unit in Mandarin Chinese word production: an intrinsic or accidental property of the production system?","volume":"20","author":"TM Chen","year":"2013","journal-title":"Psychonomic Bulletin & Review"},{"key":"ref2","first-page":"960","article-title":"A method for continuous speech segmentation using HMM","volume":"2","author":"S Nakagawa","year":"1988","journal-title":"International Conference on Pattern Recognition"},{"key":"ref3","first-page":"357","article-title":"Automatic segmentation and labeling of speech based on hidden markov models","volume":"12","author":"F Brugnara","year":"1993","journal-title":"Automatic segmentation and labeling of speech based on hidden markov models"},{"key":"ref4","first-page":"13","article-title":"Syllable recognition using syllable-segment statistics and syllable-based HMM","volume":"101","author":"N Takahashi","year":"2002","journal-title":"International Conference on Spoken Language Processing"},{"key":"ref5","unstructured":"Pawate BI, Dowling E. A HMM-based approach for segmenting continuous speech. Signals, Systems and Computers, 1992. 1992 Conference Record of The Twenty-Sixth Asilomar Conference on. 1992; 2: 1105\u20131110."},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"Reichl W, Ruske G. Syllable segmentation of continuous speech with artificial neural networks. European Conference on Speech Communication and Technology, Eurospeech 1993, Berlin, Germany, September. 1993; 279\u2013280: 277\u2013278.","DOI":"10.21437\/Eurospeech.1993-182"},{"key":"ref7","first-page":"580","article-title":"Robust Syllable Segmentation of Continuous Speech Using Neural Networks","author":"A Noetzel","year":"1991","journal-title":"Electro International"},{"key":"ref8","first-page":"615","article-title":"A Segmentation Method for Continuous Speech Utilizing Hybrid Neuro-Fuzzy Network","volume":"15","author":"CT Hsieh","year":"1999","journal-title":"Journal of Information Science & Engineering"},{"issue":"1","key":"ref9","first-page":"1721","article-title":"Syllable detection and segmentation using temporal ow neural networks","volume":"910","author":"L Shastri","year":"1999","journal-title":"Proceedings of the Fourteenth International Congress of Phonetic Sciences"},{"key":"ref10","first-page":"3438","article-title":"Neural network boundary refining for automatic speech segmentation. icassp","volume":"6","author":"DT Toledano","year":"2000","journal-title":"IEEE Computer Society"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"Sethy A, Narayanan SS. Refined speech segmentation for concatenative speech synthesis. International Conference on Spoken Language Processing, Icslp2002\u2014INTERSPEECH 2002, Denver, Colorado, Usa, September. 2002.","DOI":"10.21437\/ICSLP.2002-89"},{"key":"ref12","unstructured":"Jia Z. GMM based connected digits speech recognizer and the state of the art of the language modeling for large vocabulary speech recognizer. Doctoral dissertation, Suzhou University. 2006."},{"key":"ref13","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1109\/10.477699","article-title":"A noninvasive technique for detecting hypernasal speech using a nonlinear operator","volume":"43","author":"DA Cairns","year":"1996","journal-title":"IEEE transactions on bio-medical engineering"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TBME.2006.889191","article-title":"Acoustic analysis and detection of hypernasality using a group delay function","volume":"54","author":"P Vijayalakshmi","year":"2007","journal-title":"IEEE transactions on bio-medical engineering"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"Vijayalakshmi P, Nagarajan T, Rav J. Selective pole modification-based technique for the analysis and detection of hypernasality. TENCON 2009\u20132009 IEEE Region 10 Conference. 2009: 1\u20135.","DOI":"10.1109\/TENCON.2009.5396117"},{"key":"ref16","first-page":"1","article-title":"Pattern recognition of hypernasality in voice of patients with Cleft and Lip Palate","author":"RG Nieto","year":"2014","journal-title":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision"},{"issue":"7","key":"ref17","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1114\/1.1380422","article-title":"A noninvasive estimation of hypernasality using a linear predictive model","volume":"29","author":"DK Rah","year":"2001","journal-title":"Annals of Biomedical Engineering"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"Zhang X, Li G, Qiao F. A Speech Endpoint Detection Algorithm Based on Entropy and RBF Neural Network IEEE International Conference on Granular Computing. IEEE Computer Society. 2007: 506.","DOI":"10.1109\/GrC.2007.95"},{"issue":"2","key":"ref19","first-page":"181","article-title":"Speech Endpoint Detection Algorithm Analysis Based on Short-term Energy Ratio","volume":"42","author":"YH Dai","year":"2009","journal-title":"Communications Technology"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"Zhang T, Huang H, He L, Lech M. A robust speech endpoint detection algorithm based on wavelet packet and energy entropy. International Conference on Computer Science and Network Technology. 2013: 1050\u20131054.","DOI":"10.1109\/ICCSNT.2013.6967284"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"Jin L, Cheng J. An Improved Speech Endpoint Detection Based on Spectral Subtraction and Adaptive Sub-band Spectral Entropy. International Conference on Intelligent Computation Technology and Automation. 2010:591\u2013594.","DOI":"10.1109\/ICICTA.2010.309"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"Guo Q, Li N, Ji G. A improved dual-threshold speech endpoint detection algorithm. International Conference on Computer and Automation Engineering. 2010: 123\u2013126.","DOI":"10.1109\/ICCAE.2010.5451414"},{"key":"ref23","unstructured":"Zhao X, O'Shaughnessy D. A new hybrid approach for automatic speech signal segmentation using silence signal detection, energy convex hull, and spectral variation. Electrical and Computer Engineering, 2008. CCECE 2008. Canadian Conference on. 2008: 145\u2013148."},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"Li J, Shen F. Automatic segmentation of Chinese Mandarin speech into syllable-like. International Conference on Asian Language Processing. 2016: 57\u201360.","DOI":"10.1109\/IALP.2015.7451531"},{"issue":"3","key":"ref25","first-page":"339","article-title":"Initial\/final segmentation using loss function and acoustic features","volume":"37","author":"H Li","year":"2012","journal-title":"Acta Acustica"},{"key":"ref26","first-page":"104","article-title":"Boundary detection of Chinese initials and finals based on seneff's auditory spectrum features","volume":"37","author":"B Chen","year":"2012","journal-title":"Acta Acustica"},{"key":"ref27","article-title":"Research on speech endpoint detection and initial\/final segmentation based on the dual-threshold algorithm","author":"D Lu","year":"2011","journal-title":"Journal of Guilin University of Electronic Technology"},{"key":"ref28","unstructured":"Sheng H., Qiang H., Youwei Z. A Method for Chinese Consonant\/Vowl Dividing Based on Wavelet Transform. Proceedings of Signal processing branch of China electronic institute. The 9th national conference on the signal processing, 1999."},{"key":"ref29","article-title":"Entropy-based initial\/final segmentation for Chinese whispered speech","author":"X Li","year":"2005","journal-title":"Acta Acustica"},{"key":"ref30","first-page":"35","article-title":"Linguistics Phonetics","author":"X Lin","year":"2013"},{"article-title":"Assessment and Treatment of Cleft Palate Speech","year":"2015","author":"Y Li","key":"ref31"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"331","DOI":"10.3109\/13682829609031326","article-title":"Characteristics of cleft palate speech","volume":"31","author":"A Harding","year":"1996","journal-title":"Eur. J. Disord. Commun"},{"key":"ref33","first-page":"19","article-title":"Therapy techniques for cleft palate speech& Related disorder","author":"KJ Golding-Kushner","year":"2001","journal-title":"Thomson Learning Inc"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1109\/LSP.2014.2311435","article-title":"Time-Frequency Feature and AMS-GMM Mask for Acoustic Emotion Classification","volume":"21","author":"L Zao","year":"2014","journal-title":"IEEE Signal Processing Letters"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.specom.2017.05.005","article-title":"Text-independent speaker identification using robust statistics estimation","volume":"92","author":"ME Ayadi","year":"2017","journal-title":"Speech Communication"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.sigpro.2015.09.002","article-title":"Independent vector analysis followed by HMM-based feature enhancement for robust speech recognition","volume":"120","author":"JW Cho","year":"2016","journal-title":"Signal Processing"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"2101","DOI":"10.1016\/j.sigpro.2011.03.020","article-title":"Context-adaptive pre-processing scheme for robust speech recognition in fast-varying noise environment","volume":"91","author":"I Mporas","year":"2011","journal-title":"Signal Processing"},{"key":"ref38","first-page":"37","article-title":"A new logarithmic energy feature for endpoint detection","volume":"6","author":"SC Xiao","year":"2004","journal-title":"Audio Engineering"},{"key":"ref39","first-page":"701","article-title":"Segmentation of chinese initials and finals based on auditory event detection","volume":"35","author":"B Zhang","year":"2010","journal-title":"Acta Acustica"},{"key":"ref40","first-page":"134","article-title":"I\/f segmentation for chinese continuous speech based on vowel detection","volume":"47","author":"Y Wang","year":"2011","journal-title":"Computer Engineering & Applications"},{"key":"ref41","first-page":"49","article-title":"I\/f segmentation for mandarin speech based on fuzzy-rough neural network","volume":"32","author":"M Su","year":"2008","journal-title":"Audio Engineering"},{"key":"ref42","first-page":"90","article-title":"Research on i\/f segmentation in continuous mandarin speech","volume":"17","author":"YJ Liu","year":"2005","journal-title":"Journal of Gansu Sciences"},{"issue":"2","key":"ref43","first-page":"20","article-title":"Initial\/final segmentation of chinese whispered speech based on the auditory model","volume":"23","author":"H Ding","year":"2004","journal-title":"Applied Acoustics"},{"issue":"1","key":"ref44","first-page":"99","article-title":"The structure of the mandarin syllable: why, when and how to teach it","volume":"79","author":"H Triskova","year":"2011","journal-title":"Archiv Orient\u00e1ln\u00ed"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pone.0184267","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T20:27:35Z","timestamp":1750883255000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0184267"}},"subtitle":[],"editor":[{"given":"Philip","family":"Allen","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2017,9,19]]},"references-count":44,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2017,9,19]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0184267","relation":{},"ISSN":["1932-6203"],"issn-type":[{"type":"electronic","value":"1932-6203"}],"subject":[],"published":{"date-parts":[[2017,9,19]]}}}