{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:36:49Z","timestamp":1760132209809},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,6,27]],"date-time":"2012-06-27T00:00:00Z","timestamp":1340755200000},"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":[[2013,3]]},"DOI":"10.1007\/s10772-012-9162-4","type":"journal-article","created":{"date-parts":[[2012,6,27]],"date-time":"2012-06-27T13:57:44Z","timestamp":1340805464000},"page":"89-101","source":"Crossref","is-referenced-by-count":27,"title":["Non-intrusive speech quality assessment using several combinations of auditory features"],"prefix":"10.1007","volume":"16","author":[{"given":"Rajesh Kumar","family":"Dubey","sequence":"first","affiliation":[]},{"given":"Arun","family":"Kumar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,6,27]]},"reference":[{"key":"9162_CR1","unstructured":"ITU-T Recommendation P.800 (1996). Methods for subjective determination of transmission quality. International Telecommunication Union-Telecommunication Standardization Sector, Geneva."},{"key":"9162_CR2","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1023\/A:1026550713198","volume":"3","author":"T. Fegyo","year":"2000","unstructured":"Fegyo, T., Szarvas, M., Tatai, P., & Gordos, G. (2000). Objective speech quality estimation for analog mobile channels: problems and solutions. International Journal of Speech Technology, 3, 277\u2013287.","journal-title":"International Journal of Speech Technology"},{"key":"9162_CR3","unstructured":"ITU-T Recommendation P.862 (1996). Perceptual evaluation of speech quality (PESQ), an objective method for end-to-end speech quality assessment of narrow-band telephone networks. International Telecommunication Union-Telecommunication Standardization Sector, Geneva."},{"key":"9162_CR4","unstructured":"ITU-T Recommendation P.861 (1996). Objective quality measurement of telephone band (300\u20133400 Hz) speech codecs. International Telecommunication Union-Telecommunication Standardization Sector, Geneva."},{"key":"9162_CR5","unstructured":"ITU-T Recommendation P.563 (2004). Single ended method for objective speech quality assessment in narrow-band telephony applications. International Telecommunication Union- Telecommunication Standardization Sector, Geneva."},{"key":"9162_CR6","first-page":"1719","volume-title":"IEEE 44th vehicular technology conf.","author":"J. Liang","year":"1994","unstructured":"Liang, J., & Kubichek, R. (1994). Output based objective speech quality. In IEEE 44th vehicular technology conf. (Vol.\u00a03(8\u201310), pp. 1719\u20131723)."},{"key":"9162_CR7","first-page":"666","volume-title":"Proc. 4th international conf. on signal processing","author":"O. C. Au","year":"1998","unstructured":"Au, O. C., & Lam, K. (1998). A novel output based objective speech quality measure for wireless communication. In Proc. 4th international conf. on signal processing (Vol.\u00a01, pp. 666\u2013669)."},{"issue":"6","key":"9162_CR8","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1049\/ip-vis:20000539","volume":"147","author":"P. Gray","year":"2000","unstructured":"Gray, P., Hollier, M., & Massara, R. (2000). Non-intrusive speech quality assessment using vocal-tract models. IEE Proceedings. Vision, Image and Signal Processing, 147(6), 493\u2013501.","journal-title":"IEE Proceedings. Vision, Image and Signal Processing"},{"issue":"6","key":"9162_CR9","doi-asserted-by":"crossref","first-page":"1924","DOI":"10.1109\/TASL.2006.883177","volume":"14","author":"L. Malfait","year":"2006","unstructured":"Malfait, L., Berger, J., & Kastner, M. (2006). P.563-The ITU-T standard for single-ended speech quality assessment. IEEE Transactions on Audio, Speech, and Language Processing, 14(6), 1924\u20131934.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"5","key":"9162_CR10","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1109\/TSA.2005.851924","volume":"13","author":"D. S. Kim","year":"2005","unstructured":"Kim, D. S. (2005). ANIQUE: an auditory model for single ended speech quality estimation. IEEE Transactions on Audio, Speech, and Language Processing, 13(5), 821\u2013831.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"6","key":"9162_CR11","doi-asserted-by":"crossref","first-page":"1948","DOI":"10.1109\/TASL.2006.883250","volume":"14","author":"V. Grancharov","year":"2006","unstructured":"Grancharov, V., Zhao, D. Y., Lindblom, J., & Kleijn, W. B. (2006). Low-complexity, non-intrusive speech quality assessment. IEEE Transactions on Audio, Speech, and Language Processing, 14(6), 1948\u20131956.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9162_CR12","first-page":"125","volume-title":"Proc. IEEE international conf. on acoustics, speech and signal processing","author":"T. Falk","year":"2005","unstructured":"Falk, T., Xu, Q., & Chan, W. Y. (2005). Non-intrusive GMM based speech quality measurement. In Proc. IEEE international conf. on acoustics, speech and signal processing (Vol.\u00a01, pp. 125\u2013128)."},{"key":"9162_CR13","first-page":"385","volume-title":"Proc. IEEE international conf. on acoustics, speech and signal processing","author":"G. Chen","year":"2006","unstructured":"Chen, G., & Parsa, V. (2006). Bayesian model based non-intrusive speech quality evaluation. In Proc. IEEE international conf. on acoustics, speech and signal processing (Vol.\u00a01, pp. 385\u2013388)."},{"key":"9162_CR14","first-page":"837","volume-title":"Proc. IEEE international conf. on acoustics, speech and signal processing","author":"T. Falk","year":"2006","unstructured":"Falk, T., & Chan, W. Y. (2006a). Enhanced non-intrusive speech quality measurement using degradation models. In Proc. IEEE international conf. on acoustics, speech and signal processing (Vol.\u00a01, pp. 837\u2013840)."},{"issue":"6","key":"9162_CR15","doi-asserted-by":"crossref","first-page":"1935","DOI":"10.1109\/TASL.2006.883253","volume":"14","author":"T. Falk","year":"2006","unstructured":"Falk, T., & Chan, W. Y. (2006b). Single-ended speech quality measurement using machine learning methods. IEEE Transactions on Audio, Speech, and Language Processing, 14(6), 1935\u20131947.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"5","key":"9162_CR16","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1109\/LSP.2005.845604","volume":"12","author":"G. Chen","year":"2005","unstructured":"Chen, G., & Parsa, V. (2005). Non-intrusive speech quality evaluation using an adaptive neuro-fuzzy inference system. IEEE Signal Processing Letters, 12(5), 403\u2013406.","journal-title":"IEEE Signal Processing Letters"},{"key":"9162_CR17","unstructured":"Slaney, M. (1988). Lyon\u2019s cochlear model. Advanced technology group, apple technical report no.\u00a013, Apple Computer Inc."},{"key":"9162_CR18","first-page":"1282","volume-title":"Proc. IEEE international conf. on acoustics, speech and signal processing","author":"R. F. Lyon","year":"1982","unstructured":"Lyon, R. F. (1982). A\u00a0computational model of filtering, detection, and compression in the cochlea. In Proc. IEEE international conf. on acoustics, speech and signal processing (pp. 1282\u20131285)."},{"key":"9162_CR19","first-page":"4176","volume-title":"Proc. IEEE international conf. on acoustics, speech and signal processing","author":"Z. Jing","year":"2002","unstructured":"Jing, Z., & Johnson, M. H. (2002). Auditory modeling inspired methods of feature extraction for robust automatic speech recognition. In Proc. IEEE international conf. on acoustics, speech and signal processing (Vol.\u00a04, pp. 4176\u20134179)."},{"key":"9162_CR20","unstructured":"ITU-T Recommendation P. Supplement-23 (1998). ITU-T Coded-Speech database (1998). International telecommunication union-telecommunication standardization sector, Geneva."},{"issue":"1","key":"9162_CR21","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TASL.2007.911054","volume":"16","author":"Y. Hu","year":"2008","unstructured":"Hu, Y., & Loizou, P. C. (2008). Evaluation of objective quality measures for speech enhancement. IEEE Transactions on Audio, Speech, and Language Processing, 16(1), 229\u2013238.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9162_CR22","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1016\/j.specom.2006.12.006","volume":"49","author":"Y. Hu","year":"2007","unstructured":"Hu, Y., & Loizou, P. C. (2007). Subjective comparison and evaluation of speech enhancement algorithms. Speech Communications, 49, 588\u2013601.","journal-title":"Speech Communications"},{"key":"9162_CR23","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/978-3-642-11301-7_34","volume-title":"Advances in multimedia modeling","author":"M. Narwaria","year":"2010","unstructured":"Narwaria, M., Lin, W., McLoughlin, I. V., Emmanuel, S., & Tien, C. L. (2010). Non-intrusive speech quality assessment with support vector regression. In Advances in multimedia modeling, 16th International multimedia modeling conf. (Vol.\u00a05916, pp. 325\u2013335). Berlin: Springer."},{"key":"9162_CR24","first-page":"565","volume-title":"3rd international conf. on electrical & computer engineering","author":"M. R. Hasan","year":"2004","unstructured":"Hasan, M. R., Jamil, M., Rabbani, M. G., & Rahman, M. S. (2004). Speaker identification using mel frequency cepstral coefficients. In 3rd international conf. on electrical & computer engineering (pp. 565\u2013568). Dhaka: ICECE."},{"key":"9162_CR25","doi-asserted-by":"crossref","first-page":"3708","DOI":"10.1109\/ICPR.2010.903","volume-title":"IEEE international conf. on pattern recognition","author":"E. Bozkurt","year":"2010","unstructured":"Bozkurt, E., Erzin, E., Erdem, C. E., & Erdem, A. T. (2010). Use of line spectral frequencies for emotion recognition from speech. In IEEE international conf. on pattern recognition, Turkey (pp. 3708\u20133711)."},{"key":"9162_CR26","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H. Hermansky","year":"1990","unstructured":"Hermansky, H. (1990). Perceptual linear predictive (PLP) analysis of speech. The Journal of the Acoustical Society of America, 87, 1738\u20131752.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"2","key":"9162_CR27","doi-asserted-by":"crossref","first-page":"111","DOI":"10.4103\/0377-2063.63087","volume":"56","author":"K. Audhkhasi","year":"2010","unstructured":"Audhkhasi, K., & Kumar, A. (2010). Two scale auditory features based non-intrusive speech quality evaluation. IETE Journal of Research, 56(2), 111\u2013118.","journal-title":"IETE Journal of Research"},{"issue":"1","key":"9162_CR28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A. P. Dempster","year":"1977","unstructured":"Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society. Series B. Methodological, 39(1), 1\u201338.","journal-title":"Journal of the Royal Statistical Society. Series B. Methodological"},{"issue":"6","key":"9162_CR29","doi-asserted-by":"crossref","first-page":"1912","DOI":"10.1109\/TASL.2006.883257","volume":"14","author":"A. Karmakar","year":"2006","unstructured":"Karmakar, A., Kumar, A., & Patney, R. K. (2006). A multiresolution model of auditory excitation pattern and its application to objective evaluation of perceived speech quality. IEEE Transactions on Audio, Speech, and Language Processing, 14(6), 1912\u20131923.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9162_CR30","volume-title":"Digital processing of speech signals","author":"L. R. Rabiner","year":"1978","unstructured":"Rabiner, L. R., & Schafer, R. W. (1978). Digital processing of speech signals. Englewood: Prentice-Hall."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9162-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-012-9162-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9162-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T04:10:11Z","timestamp":1714104611000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-012-9162-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,27]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,3]]}},"alternative-id":["9162"],"URL":"https:\/\/doi.org\/10.1007\/s10772-012-9162-4","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,6,27]]}}}