{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T02:10:14Z","timestamp":1722219014880},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2019,12,23]],"date-time":"2019-12-23T00:00:00Z","timestamp":1577059200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,12,23]],"date-time":"2019-12-23T00:00:00Z","timestamp":1577059200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1007\/s11265-019-01510-4","type":"journal-article","created":{"date-parts":[[2019,12,23]],"date-time":"2019-12-23T02:02:37Z","timestamp":1577066557000},"page":"831-838","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Simultaneous Estimation of Glottal Source Waveforms and Vocal Tract Shapes from Speech Signals Based on ARX-LF Model"],"prefix":"10.1007","volume":"92","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-7884-0462","authenticated-orcid":false,"given":"Yongwei","family":"Li","sequence":"first","affiliation":[]},{"given":"Ken-Ichi","family":"Sakakibara","sequence":"additional","affiliation":[]},{"given":"Masato","family":"Akagi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,23]]},"reference":[{"issue":"5","key":"1510_CR1","doi-asserted-by":"publisher","first-page":"3246","DOI":"10.1121\/1.411700","volume":"97","author":"J Cohen","year":"1995","unstructured":"Cohen, J., Kamm, T., Andreou, A.G. (1995). Vocal tract normalization in speech recognition: Compensating for systematic speaker variability. The Journal of the Acoustical Society of America, 97(5), 3246\u20133247.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"1510_CR2","doi-asserted-by":"crossref","unstructured":"Raitio, T., Suni, A., Pulakka, H., Vainio, M., Alku, P. (2011). Utilizing glottal source pulse library for generating improved excitation signal for HMM-based speech synthesis. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4564\u20134567).","DOI":"10.1109\/ICASSP.2011.5947370"},{"key":"1510_CR3","doi-asserted-by":"crossref","unstructured":"Drugman, T., Dubuisson, T., Dutoit, T. (2009). On the mutual information between source and filter contributions for voice pathology detection. In Tenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2009-447"},{"issue":"2","key":"1510_CR4","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/0167-6393(94)00050-K","volume":"16","author":"DG Childers","year":"1995","unstructured":"Childers, D.G. (1995). Glottal source modeling for voice conversion. Speech Communication, 16(2), 127\u2013138.","journal-title":"Speech Communication"},{"issue":"5","key":"1510_CR5","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/89.784109","volume":"7","author":"MD Plumpe","year":"1999","unstructured":"Plumpe, M.D., Quatieri, T.F., Reynolds, D.A. (1999). Modeling of the glottal flow derivative waveform with application to speaker identification. IEEE Transactions on Speech and Audio Processing, 7(5), 569\u2013586.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"1510_CR6","doi-asserted-by":"crossref","unstructured":"Iliev, A.I., Scordilis, M.S., Papa, J.P., Falc\u00e3o, A.X. (2010). Spoken emotion recognition through optimum-path forest classification using glottal features. Computer Speech & Language, pp. 445\u2013460.","DOI":"10.1016\/j.csl.2009.02.005"},{"key":"1510_CR7","doi-asserted-by":"crossref","unstructured":"Li, X., & Akagi, M. (2018). A three-layer emotion perception model for valence and arousal-based detection from multilingual speech. In Interspeech (pp. 3643\u20133647).","DOI":"10.21437\/Interspeech.2018-1820"},{"key":"1510_CR8","first-page":"1","volume":"4","author":"G Fant","year":"1985","unstructured":"Fant, G., Liljencrants, J., Lin, Q.g. (1985). A four-parameter model of glottal flow. STL-QPSR, 4, 1\u201313.","journal-title":"STL-QPSR"},{"key":"1510_CR9","unstructured":"Rabiner, L.R., & Schafer, R.W. (1987). Digital processing of speech signals. Prentice-hall Englewood Cliffs, NJ, 100."},{"issue":"4","key":"1510_CR10","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1109\/TASSP.1979.1163260","volume":"27","author":"D Wong","year":"1979","unstructured":"Wong, D., Markel, J., Gray, A. (1979). Least squares glottal inverse filtering from the acoustic speech waveform. IEEE Transactions on Acoustics, Speech, and Signal Processing, 27(4), 350\u2013355.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"2-3","key":"1510_CR11","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/0167-6393(92)90005-R","volume":"11","author":"P Alku","year":"1992","unstructured":"Alku, P. (1992). Glottal wave analysis with pitch synchronous iterative adaptive inverse filtering. Speech Communication, 11(2-3), 109\u2013118.","journal-title":"Speech Communication"},{"key":"1510_CR12","unstructured":"Drugman, T., Bozkurt, B., Dutoit, T. Complex cepstrum-based decomposition of speech for glottal source estimation. Interspeech, 116\u2013119."},{"issue":"3","key":"1510_CR13","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1016\/j.specom.2012.12.004","volume":"55","author":"J Kane","year":"2013","unstructured":"Kane, J., & Gobl, C. (2013). Automating manual user strategies for precise voice source analysis. Speech Communication, 55(3), 397\u2013414.","journal-title":"Speech Communication"},{"issue":"2","key":"1510_CR14","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1121\/1.398894","volume":"87","author":"DH Klatt","year":"1990","unstructured":"Klatt, D.H., & Klatt, L.C. (1990). Analysis, synthesis, and perception of voice quality variations among female and male talkers. The Journal of the Acoustical Society of America, 87(2), 820\u2013857.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"1510_CR15","doi-asserted-by":"publisher","first-page":"1605","DOI":"10.1109\/ICASSP.1986.1169239","volume":"11","author":"H Fujisaki","year":"1986","unstructured":"Fujisaki, H., & Ljungqvist, M. (1986). Proposal and evaluation of models for the glottal source waveform. ICASSP\u201986. IEEE International Conference on Acoustics, Speech, and Signal Processing, 11, 1605\u20131608.","journal-title":"IEEE International Conference on Acoustics, Speech, and Signal Processing"},{"issue":"6","key":"1510_CR16","first-page":"738","volume":"78","author":"W Ding","year":"1995","unstructured":"Ding, W., Kasuya, H., Adachi, S. (1995). Simultaneous estimation of vocal tract and voice source parameters based on an ARX model. IEICE Transactions on Information and Systems, 78(6), 738\u2013743.","journal-title":"IEICE Transactions on Information and Systems"},{"key":"1510_CR17","doi-asserted-by":"crossref","unstructured":"Fujisaki, H., & Ljungqvist, M. (1996). Estimation of voice source and vocal tract parameters based on ARMA analysis and a model for the glottal source waveform. In Recent Research Towards Advanced Man-machine Interface Through Spoken Language (pp. 52\u201360).","DOI":"10.1016\/B978-044481607-8\/50051-7"},{"issue":"1","key":"1510_CR18","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1121\/1.1379076","volume":"110","author":"M Fr\u00f6hlich","year":"2001","unstructured":"Fr\u00f6hlich, M., Michaelis, D., Strube, H.W. (2001). SIM-simultaneous inverse filtering and matching of a glottal flow model for acoustic speech signals. The Journal of the Acoustical Society of America, 110(1), 479\u2013488.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"1510_CR19","doi-asserted-by":"crossref","unstructured":"Vincent, D., Rosec, O., Chonavel, T. (2005). Estimation of LF glottal source parameters based on an ARX model. In Ninth European Conference on Speech Communication and Technology (pp. 333\u2013336).","DOI":"10.21437\/Interspeech.2005-177"},{"issue":"2","key":"1510_CR20","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1109\/TSA.2005.857807","volume":"14","author":"Q Fu","year":"2006","unstructured":"Fu, Q., & Murphy, P. (2006). Robust glottal source estimation based on joint source-filter model optimization. IEEE Transactions on Audio, Speech, and Language Processing, 14(2), 492\u2013501.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"1510_CR21","first-page":"119","volume":"2","author":"G Fant","year":"1995","unstructured":"Fant, G. (1995). The LF-model revisited Transformations and frequency domain analysis. Speech Trans. Lab. Q. Rep., Royal Inst. of Tech. Stockholm, 2(3), 119\u2013156.","journal-title":"Speech Trans. Lab. Q. Rep., Royal Inst. of Tech. Stockholm"},{"key":"1510_CR22","unstructured":"Li, Y., Sakakibara, K.I., Morikawa, D., Akagi, M. (2017). Commonalities of glottal sources and vocal tract shapes among speakers in emotional speech. In International Seminar on Speech Production (pp. 24\u201334)."},{"key":"1510_CR23","doi-asserted-by":"crossref","unstructured":"Takahashi, K., & Akagi, M. (2018). Estimation of glottal source waveforms and vocal tract shape for singing voices with wide frequency range. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (pp. 1879\u20131887).","DOI":"10.23919\/APSIPA.2018.8659480"},{"issue":"3","key":"1510_CR24","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1109\/TASL.2011.2170835","volume":"20","author":"T Drugman","year":"2012","unstructured":"Drugman, T., Thomas, M., Gudnason, J., Naylor, P., Dutoit, T. (2012). Detection of glottal closure instants from speech signals: A quantitative review. IEEE Transactions on Audio, Speech, and Language Processing, 20(3), 994\u20131006.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"1510_CR25","doi-asserted-by":"crossref","first-page":"143","DOI":"10.21437\/SpeechProsody.2012-39","volume":"2012","author":"J Kane","year":"2012","unstructured":"Kane, J., Yanushevskaya, I., N\u00ed Chasaide, A., Gobl, C. (2012). Exploiting time and frequency domain measures for precise voice source parameterisation. Speech Prosody, 2012, 143\u2013146.","journal-title":"Speech Prosody"},{"key":"1510_CR26","unstructured":"Lu, H.L. (2002). Toward a high-quality singing synthesizer with vocal texture control. Stanford University."},{"key":"1510_CR27","doi-asserted-by":"crossref","unstructured":"Kawahara, H., Sakakibara, K.I., Banno, H., Morise, M., Toda, T., Irino, T. (2015). Aliasing-free implementation of discrete-time glottal source models and their applications to speech synthesis and F0 extractor evaluation. In Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2015 Asia-Pacific (pp. 520\u2013529).","DOI":"10.1109\/APSIPA.2015.7415325"},{"issue":"1","key":"1510_CR28","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.csl.2011.03.003","volume":"26","author":"T Drugman","year":"2012","unstructured":"Drugman, T., Bozkurt, B., Dutoit, T. (2012). A comparative study of glottal source estimation techniques. Computer Speech & Language, 26(1), 20\u201334.","journal-title":"Computer Speech & Language"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-019-01510-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-019-01510-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-019-01510-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T01:35:15Z","timestamp":1722216915000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-019-01510-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,23]]},"references-count":28,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2020,8]]}},"alternative-id":["1510"],"URL":"https:\/\/doi.org\/10.1007\/s11265-019-01510-4","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,23]]},"assertion":[{"value":"14 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}