{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T22:24:34Z","timestamp":1761863074038},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2011,10,12]],"date-time":"2011-10-12T00:00:00Z","timestamp":1318377600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2011,12]]},"DOI":"10.1007\/s10772-011-9119-z","type":"journal-article","created":{"date-parts":[[2011,10,11]],"date-time":"2011-10-11T13:59:41Z","timestamp":1318341581000},"page":"393-403","source":"Crossref","is-referenced-by-count":13,"title":["Combining formant frequency based on variable order LPC coding with acoustic features for TIMIT phone recognition"],"prefix":"10.1007","volume":"14","author":[{"given":"Zaineb","family":"Ben Messaoud","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Ben Hamida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,10,12]]},"reference":[{"issue":"2","key":"9119_CR1","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1121\/1.1912679","volume":"50","author":"B. S. Atal","year":"1971","unstructured":"Atal, B. S., & Hanauer, S. L. (1971). Speech analysis and synthesis by linear prediction of the speech wave. The Journal of the Acoustical Society of America, 50(2), 637\u2013655.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"3","key":"9119_CR2","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/TASSP.1976.1162800","volume":"24","author":"B. S. Atal","year":"1976","unstructured":"Atal, B. S., & Rabiner, L. R. (1976). A pattern recognition approach to voiced-unvoiced-silence classification with application to speech recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 24(3), 201\u2013212.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9119_CR3","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1016\/j.specom.2007.02.006","volume":"49","author":"M. Benzeghiba","year":"2007","unstructured":"Benzeghiba, M., De Mori, R., Deroo, O., Dupont, S., Erbes, T., Jouvet, D., Fissore, L., Laface, P., Mertins, A., Ris, C., Rose, R., Tyagi, V., & Wellekens, C. (2007). Automatic speech recognition and speech variability: a review. Speech Communication, 49, 763\u2013786.","journal-title":"Speech Communication"},{"key":"9119_CR4","unstructured":"Ben Messaoud, Z., Gargouri, D., Zribi, S., & Ben Hamida, A. (2009). Formant tracking linear prediction model using HMMs for noisy speech processing. International Journal of Signal Processing, WASET, 291\u2013296."},{"key":"9119_CR5","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1109\/MELCON.2010.5476290","volume-title":"15th IEEE mediterranean electrotechnical conference","author":"Z. Ben Messaoud","year":"2010","unstructured":"Ben Messaoud, Z., & Ben Hamida, A. (2010). CDHMM parameters selection for speaker-independent phone recognition in continuous speech system. In 15th IEEE mediterranean electrotechnical conference, Valletta, Malta (pp. 253\u2013258)."},{"key":"9119_CR6","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"ASSP-28","author":"S. Davis","year":"1980","unstructured":"Davis, S., & Mermelstein, P. (1980). Comparison of parametric representations of monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP-28, 357\u2013366.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9119_CR7","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1006\/csla.2001.0171","volume":"15","author":"R. Mori De","year":"2001","unstructured":"De Mori, R., Moisa, L., Gemello, R., Mana, F., & Albensano, D. (2001). Augmenting standard speech recognition features with energy gravity centres. Computer Speech and Language, 15, 341\u2013354.","journal-title":"Computer Speech and Language"},{"issue":"12","key":"9119_CR8","doi-asserted-by":"crossref","first-page":"1737","DOI":"10.1121\/1.1908558","volume":"33","author":"H. K. Dunn","year":"1961","unstructured":"Dunn, H. K. (1961). Methods of measuring vowel formant bandwidths. The Journal of the Acoustical Society of America, 33(12), 1737\u20131746.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9119_CR9","first-page":"347","volume-title":"IEEE automatic speech recognition and understanding workshop","author":"J. G. Fiscus","year":"1997","unstructured":"Fiscus, J. G. (1997). A post-processing system to yield reduced word error rates: recognizer output voting error reduction (rover). In IEEE automatic speech recognition and understanding workshop, Santa Barbara, CA (pp. 347\u2013354)."},{"issue":"2","key":"9119_CR10","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/89.985541","volume":"10","author":"M. J. F. Gales","year":"2002","unstructured":"Gales, M. J. F. (2002). Maximum likelihood multiple subspace projections for hidden Markov models. IEEE Transactions on Speech and Audio Processing, 10(2), 37\u201347.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"1","key":"9119_CR11","first-page":"221","volume":"45","author":"D. Gargouri","year":"2008","unstructured":"Gargouri, D., Zerzri, M. A., & Ben Hamida, A. (2008). Formants estimation algorithm in noisy environment. GESTS International Transaction on Computer Science and Engineering, 45(1), 221\u2013241.","journal-title":"GESTS International Transaction on Computer Science and Engineering"},{"key":"9119_CR12","first-page":"2083","volume-title":"European conf. on speech communication and technology","author":"J. N. Holmes","year":"1997","unstructured":"Holmes, J. N., Holmes, W. J., & Garner, P. N. (1997). Using formant frequencies in speech recognition. In European conf. on speech communication and technology, Rhodes, Greece (Vol. 4, pp. 2083\u20132086)."},{"key":"9119_CR13","first-page":"1","volume-title":"IEEE international conference on acoustics, speech, and signal processing","author":"W. J. Holmes","year":"1998","unstructured":"Holmes, W. J., & Garner, P. N. (1998). On robust incorporation of format features into hidden Markov models for automatic speech recognition. In IEEE international conference on acoustics, speech, and signal processing, Istanbul, Turkey (pp. 1\u20134)."},{"key":"9119_CR14","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/0167-8655(87)90093-6","volume":"6","author":"M. J. Hunt","year":"1987","unstructured":"Hunt, M. J. (1987). Delayed decisions in speech recognition\u2014the case of formants. Pattern Recognition Letters, 6, 121\u2013137.","journal-title":"Pattern Recognition Letters"},{"key":"9119_CR15","unstructured":"Kumar, N., & Andreou, A. G. (1996). A generalization of linear discriminant analysis in maximum likelihood framework (Tech. Rep. JHU-CLSP Technical Report No. 16). Johns Hopkins University."},{"key":"9119_CR16","first-page":"815","volume-title":"Proc. ICSLP","author":"Y. Laprie","year":"1992","unstructured":"Laprie, Y., & Berger, M. O. (1992). Active models for regularizing formant trajectories. In Proc. ICSLP, Banff (pp. 815\u2013818)."},{"key":"9119_CR17","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","volume":"37","author":"K. F. Lee","year":"1989","unstructured":"Lee, K. F., & Hon, H. (1989). Speaker-independent phone recognition using hidden Markov models. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37, 1641\u20131648.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"2","key":"9119_CR18","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.inffus.2003.10.007","volume":"5","author":"K. Y. Leung","year":"2004","unstructured":"Leung, K. Y., & Siu, M. (2004). Integration of acoustic and articulatory information with application to speech recognition. Information Fusion, 5(2), 141\u2013151.","journal-title":"Information Fusion"},{"key":"9119_CR19","first-page":"449","volume-title":"7th conference on telecommunications","author":"C. Lopes","year":"2009","unstructured":"Lopes, C., & Perdig\u00e3o, F. (2009). Phonetic recognition improvements through input feature set combination and acoustic context window widening. In 7th conference on telecommunications, Conftele, Sta Maria da Feira, Portugal (Vol.\u00a01, pp. 449\u2013452)."},{"key":"9119_CR20","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1109\/TASSP.1974.1162559","volume":"ASSP-22","author":"S. McCandless","year":"1974","unstructured":"McCandless, S. (1974). An algorithm for automatic formant extraction using linear prediction spectra. IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP-22, 135\u2013141.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9119_CR21","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/S0020-0255(03)00163-4","volume":"156","author":"T. Reynolds","year":"2003","unstructured":"Reynolds, T., & Antoniou, C. (2003). Experiments in speech recognition using a modular MLP architecture for acoustic modeling. Information Sciences, 156, 39\u201354.","journal-title":"Information Sciences"},{"key":"9119_CR22","first-page":"1565","volume-title":"International conference on spoken language processing","author":"M. N. Stuttle","year":"2002","unstructured":"Stuttle, M. N., & Gales, M. J. F. (2002). Combining a Gaussian mixture model front end with MFCC parameters. In International conference on spoken language processing, Denver, CO (Vol. 3, pp. 1565\u20131568)."},{"key":"9119_CR23","unstructured":"Sorin, & Ramabadran, T. (2003). Extended advanced front end (XAFE) algorithm description. Version 1.1 (Tech. Rep. ES 202 212). ETSI STQAurora DSR Working Group."},{"key":"9119_CR24","first-page":"737","volume-title":"Proc. EUROSPEECH\u201995","author":"P. Schmid","year":"1995","unstructured":"Schmid, P., & Barnard, E. (1995). Robust N-Best Formant Tracking. In Proc. EUROSPEECH\u201995, Madrid (pp. 737\u2013740)."},{"key":"9119_CR25","first-page":"253","volume-title":"IEEE international conference on acoustics, speech, and signal processing","author":"M. L. Shire","year":"2001","unstructured":"Shire, M. L. (2001). Multi-stream ASR trained with heterogeneous reverberant environments. In IEEE international conference on acoustics, speech, and signal processing, Salt Lake City, UT (Vol. 1, pp. 253\u2013256)."},{"key":"9119_CR26","first-page":"II1-129","volume-title":"IEEE international conference on acoustics, speech, and signal processing","author":"G. Saon","year":"2000","unstructured":"Saon, G., Padmanabhan, M., Gopinath, R., & Chen, S. (2000). Maximum likelihood discriminant feature spaces. In IEEE international conference on acoustics, speech, and signal processing (Vol. 2, pp. II1-129\u2013II1-132)."},{"key":"9119_CR27","first-page":"21","volume-title":"Proc. IEEE int. conf. on acoustics, speech, and signal processing","author":"D. L. Thomson","year":"1998","unstructured":"Thomson, D. L., & Chengalvarayan, R. (1998). Use of periodicity and jitter as speech recognition feature. In Proc. IEEE int. conf. on acoustics, speech, and signal processing, Seattle, WA (Vol. 1, pp. 21\u201324)."},{"key":"9119_CR28","first-page":"797","volume-title":"IEEE international conference on acoustics, speech, and signal processing","author":"L. Welling","year":"1996","unstructured":"Welling, L., & Ney, H. (1996). A model for efficient formant estimation. In IEEE international conference on acoustics, speech, and signal processing, Atlanta, GA (Vol. 2, pp. 797\u2013801)."},{"key":"9119_CR29","volume-title":"7th international conference on spoken language processing","author":"N. J. Wilkinson","year":"2002","unstructured":"Wilkinson, N. J., & Russell, M. J. (2002). Improved phone recognition on TIMIT using formant frequency data and confidence measures. In 7th international conference on spoken language processing, Denver, CO."},{"key":"9119_CR30","first-page":"607","volume-title":"European conference on speech communication and technology","author":"K. Weber","year":"2001","unstructured":"Weber, K., Bourlard, H., & Bengio, S. (2001). Hmm2-extraction of formant features and their use for robust ASR. In European conference on speech communication and technology, Aalborg, Denmark (p. 607\u2013610)."},{"key":"9119_CR31","volume-title":"International conference on spoken language processing","author":"K. Xia","year":"2000","unstructured":"Xia, K., & Wilson, C. E. (2000). A new strategy of formant tracking based on dynamic programming. In International conference on spoken language processing, Beijing, China."},{"key":"9119_CR32","doi-asserted-by":"crossref","first-page":"4521","DOI":"10.1109\/ICASSP.2008.4518661","volume-title":"IEEE international conference on acoustics, speech, and signal processing","author":"Z. J. Yan","year":"2008","unstructured":"Yan, Z. J., Zhu, B., Hu, Y., & Wang, R. H. (2008). Minimum word classification error training of HMM for automatic speech. In IEEE international conference on acoustics, speech, and signal processing, Las Vegas, USA (pp. 4521\u20134524)."},{"key":"9119_CR33","first-page":"569","volume-title":"IEEE international conference on acoustics, speech and signal processing","author":"S. Young","year":"1992","unstructured":"Young, S. (1992). The general use of tying in phoneme-based hmm speech recognisers. In IEEE international conference on acoustics, speech and signal processing, San Francisco, California, USA (Vol.\u00a01 pp. 569\u2013572)."},{"key":"9119_CR34","unstructured":"Young, S., Kershaw, D., Odell, J., Ollason, D., Valtchev, V., & Woodland, P. (2006). The HTK book (revised for HTK version 3.4). Cambridge University Engineering Department-Speech Group. Available: http:\/\/www.htk.eng.cam.ac.uk ."},{"key":"9119_CR35","first-page":"497","volume-title":"European conference on speech communication and technology","author":"A. Zolnay","year":"2003","unstructured":"Zolnay, A., Schl\u00fcter, R., & Ney, H. (2003). Extraction methods of voicing feature for robust speech recognition. In European conference on speech communication and technology, Geneva, Switzerland (Vol.\u00a01, pp. 497\u2013500)."},{"key":"9119_CR36","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1016\/j.specom.2007.04.005","volume":"49","author":"A. Zolnay","year":"2007","unstructured":"Zolnay, A., Kocharov, D., Schlutera, R., & Hermann, N. (2007). Using multiple acoustic feature sets for speech recognition. Speech Communication, 49, 514\u2013525.","journal-title":"Speech Communication"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-011-9119-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-011-9119-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-011-9119-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T20:02:44Z","timestamp":1559246564000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-011-9119-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,10,12]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2011,12]]}},"alternative-id":["9119"],"URL":"https:\/\/doi.org\/10.1007\/s10772-011-9119-z","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,10,12]]}}}