{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:26:55Z","timestamp":1740122815843,"version":"3.37.3"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2016,10,11]],"date-time":"2016-10-11T00:00:00Z","timestamp":1476144000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100007040","name":"Singapore University of Technology and Design","doi-asserted-by":"publisher","award":["SRIS11028"],"award-info":[{"award-number":["SRIS11028"]}],"id":[{"id":"10.13039\/501100007040","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1007\/s10772-016-9377-x","type":"journal-article","created":{"date-parts":[[2016,10,11]],"date-time":"2016-10-11T09:05:47Z","timestamp":1476176747000},"page":"895-905","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Robust phoneme classification for automatic speech recognition using hybrid features and an amalgamated learning model"],"prefix":"10.1007","volume":"19","author":[{"given":"Mohammed Kamal","family":"Khwaja","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peddakota","family":"Vikash","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P.","family":"Arulmozhivarman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Lui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,10,11]]},"reference":[{"key":"9377_CR1","doi-asserted-by":"crossref","unstructured":"Biswas, A., Sahu, P.K., Bhowmick, A. and Chandra, M. (2014). Feature extraction technique using ERB like wavelet sub-band periodic and aperiodic decomposition for TIMIT phoneme recognition. In the Proceeding of the International Journal of Speech Technology (Vol. 17, Iss. 4, pp. 389\u2013399).","DOI":"10.1007\/s10772-014-9236-6"},{"key":"9377_CR2","doi-asserted-by":"crossref","unstructured":"Clarkson, P. and Moreno, P. (1999). On the use of support vector machines for phonetic classification. In Proceedings of the IEEE Transactions on Acoustics, Speech and Signal Processing (Vol. 2, pp. 585\u2013 588).","DOI":"10.1109\/ICASSP.1999.759734"},{"key":"9377_CR3","doi-asserted-by":"crossref","unstructured":"Colas, F. and Brazdil, P. (2006). Comparison of SVM and some older classification algorithms in text classification tasks. In Proceedings of the International Federation for Information (Vol. 217, pp. 169\u2013178).","DOI":"10.1007\/978-0-387-34747-9_18"},{"key":"9377_CR4","doi-asserted-by":"crossref","unstructured":"Cutajar, M., Gatt, E., Grech, I., Casha, O. and Micallef, J. (2011). Support Vector Machines with the priorities method for speaker independent phoneme recognition. In Proceedings of the IEEE International Symposium on Signal Processing and Information Technology (pp. 409\u2013414).","DOI":"10.1109\/ISSPIT.2011.6151597"},{"key":"9377_CR5","unstructured":"Demolin, D., Metens, T. and Soquet, A. (1996). Three-dimensional measurement of the vocal tract shape by MRI. In Proceedings of the International Conference on Spoken Language Processing (Vol. 1, pp. 272\u2013275)."},{"key":"9377_CR6","unstructured":"Deng, H., Beddoes, M. P., Ward, R. K., Hodgson, M. (2003). Obtaining the vocal-tract area function from the vowel sound. In Proceedings of the Journal of the Canadian Acoustical Association (Vol. 31, No. 3, pp. 40\u201341)."},{"key":"9377_CR7","volume-title":"Acoustic theory of speech production","author":"G Fant","year":"1960","unstructured":"Fant, G. (1960). Acoustic theory of speech production. The Hague: Mouton."},{"key":"9377_CR8","doi-asserted-by":"crossref","unstructured":"Ganapathiraju, A., Hamaker, J., and Picone, J. (2000). Hybrid SVM\/HMM architectures for speech recognition. In Proceedings of the Speech Transcription Workshop (Vol. 4, pp. 504\u2013507).","DOI":"10.21437\/ICSLP.2000-859"},{"key":"9377_CR9","doi-asserted-by":"crossref","unstructured":"Ladefoged, P., Harshman, R., Goldstein, L., and Rice, L. (1978). Generating vocal tract shapes from formant frequencies. In Proceedings of the Journal of the Acoustical Society of America (Vol. 64, Issue 4, pp. 1027\u20131035).","DOI":"10.1121\/1.382086"},{"key":"9377_CR10","doi-asserted-by":"crossref","unstructured":"Lee, K. F. and Hon, H. W. (1989). Speaker-independent phone recognition using hidden Markov models. In Proceedings of the IEEE Transactions on Acoustics, Speech, and Signal Processing (Vol. 37, No. 11).","DOI":"10.1109\/29.46546"},{"key":"9377_CR11","doi-asserted-by":"crossref","unstructured":"Manjunath, K.E., & Sreenivasa Rao, K. (2015). Source and system features for phone recognition. In Proceedings of the International Journal of Speech Technology (Vol. 18, Iss. 2, pp. 257\u2013270).","DOI":"10.1007\/s10772-014-9266-0"},{"key":"9377_CR12","doi-asserted-by":"crossref","unstructured":"Nahar, K.M.O., Abu Shquier, M., Al-Khatib, W.G. Al-Muhtaseb, H., Elshafei M. (2016). Arabic phonemes recognition using hybrid LVQ\/HMM model for continuous speech recognition. In the Proceedings of the International Journal of Speech Technology (pp. 1\u201314).","DOI":"10.1007\/s10772-016-9337-5"},{"key":"9377_CR13","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E. (2011). Scikit-learn: Machine learning in python. In Proceedings of the Journal of Machine Learning Research (Vol. 12, pp. 2825\u20132830)."},{"key":"9377_CR14","unstructured":"Rimah, A. and Ellouze, N. (2015). Study of phonemes confusions in hierarchical automatic phoneme recognition system. In Proceedings of the Journal of Convergence Information Technology (Vol. 10, No. 4)."},{"key":"9377_CR15","first-page":"274","volume-title":"Statistical communication and detection","author":"EA Robinson","year":"1967","unstructured":"Robinson, E. A. (1967). Statistical communication and detection (pp. 274\u2013279). New York: Hafner Publishing Company."},{"key":"9377_CR16","unstructured":"Robinson, T., Fransen, J., Pye, D., Foote, J. and Renals, S. (1995). Wsjcam0: A British English Speech Corpus for large vocabulary continuous speech recognition. In Proceedings of the IEEE Transactions on Acoustics, Speech, and Signal Processing (Vol. 1, pp. 81\u201384)."},{"issue":"5","key":"9377_CR17","doi-asserted-by":"crossref","first-page":"3231","DOI":"10.1121\/1.1869752","volume":"117","author":"BH Story","year":"2005","unstructured":"Story, B. H. (2005). A parametric model of the vocal tract area function for vowel and consonant simulation. Journal of the Acoustical Society of America, 117(5), 3231\u20133254.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9377_CR18","doi-asserted-by":"crossref","unstructured":"Story, B. H., Titze, I. R., and Hoffman, E. A. (1996). Vocal tract area functions from magnetic resonance imaging. In Proceedings of the Journal of the Acoustical Society of America (Vol. 100, No. 1, pp. 537\u2013554).","DOI":"10.1121\/1.415960"},{"key":"9377_CR19","unstructured":"Vos, R., Angus, J. A., and Story, B. H. (2014). A new algorithm for vocal tract shape extraction from singer\u2019s waveforms. In Proceedings of the 136th Audio Engineering Society Convention."},{"key":"9377_CR20","doi-asserted-by":"crossref","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. (1989). Phoneme recognition: Neural networks versus Hidden Markov models. In Proceedings of the IEEE Transactions on Acoustics, Speech, and Signal Processing (Vol. 37, No. 3).","DOI":"10.1109\/29.21701"},{"key":"9377_CR21","doi-asserted-by":"crossref","unstructured":"Wakita, H. (1973). Direct estimation of the vocal tract shape by inverse filtering of acoustic speech waveforms. In Proceedings of the IEEE Transactions on Audio and Electroacoustics (Vol. 21, Issue 5, pp. 417\u2013427).","DOI":"10.1109\/TAU.1973.1162506"},{"key":"9377_CR22","doi-asserted-by":"crossref","DOI":"10.1109\/9780470043387","volume-title":"Computational auditory scene analysis: Principles, algorithms, and applications","author":"D Wang","year":"2006","unstructured":"Wang, D., & Brown, G. J. (2006). Computational auditory scene analysis: Principles, algorithms, and applications. Hoboken: Wiley."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9377-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-016-9377-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9377-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T11:41:21Z","timestamp":1692531681000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-016-9377-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,11]]},"references-count":22,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["9377"],"URL":"https:\/\/doi.org\/10.1007\/s10772-016-9377-x","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2016,10,11]]}}}