{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T09:55:29Z","timestamp":1770976529988,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,8,20]],"date-time":"2018-08-20T00:00:00Z","timestamp":1534723200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10772-018-9537-2","type":"journal-article","created":{"date-parts":[[2018,8,20]],"date-time":"2018-08-20T14:01:56Z","timestamp":1534773716000},"page":"585-599","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Reference free speech quality estimation for diverse data condition"],"prefix":"10.1007","volume":"22","author":[{"given":"Nirupam","family":"Shome","sequence":"first","affiliation":[]},{"given":"R. H.","family":"Laskar","sequence":"additional","affiliation":[]},{"given":"Debaprasad","family":"Das","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,20]]},"reference":[{"key":"9537_CR1","doi-asserted-by":"crossref","unstructured":"Breithaupt, C., Gerkmann, T., & Martin, R. (2008). A novel a priori SNR estimation approach based on selective cepstro-temporal smoothing. In International Conference on Acoustics, Speech and Signal Processing. (pp.\u00a04897\u20134900). IEEE.","DOI":"10.1109\/ICASSP.2008.4518755"},{"issue":"5","key":"9537_CR2","doi-asserted-by":"publisher","first-page":"870","DOI":"10.1109\/TSA.2005.851940","volume":"13","author":"I Cohen","year":"2005","unstructured":"Cohen, I. (2005a). Relaxed statistical model for speech enhancement and a priori SNR estimation. IEEE Transactions on Speech and Audio Processing, 13(5), 870\u2013881.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"3","key":"9537_CR3","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.specom.2005.02.011","volume":"47","author":"I Cohen","year":"2005","unstructured":"Cohen, I. (2005b). Speech enhancement using super-Gaussian speech models and noncausal a priori SNR estimation. Speech Communication, 47(3), 336\u2013350.","journal-title":"Speech Communication"},{"key":"9537_CR4","doi-asserted-by":"crossref","unstructured":"Elshamy, S., Madhu, N., Tirry, W., & Fingscheidt, T. (2015). An iterative speech model-based a priori SNR estimator. In Sixteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2015-405"},{"issue":"6","key":"9537_CR5","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","volume":"32","author":"Y Ephraim","year":"1984","unstructured":"Ephraim, Y., & Malah, D. (1984). Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator. IEEE Transactions on Acoustics, Speech, and Signal Processing, 32(6), 1109\u20131121.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"2","key":"9537_CR6","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1109\/TASSP.1985.1164550","volume":"33","author":"Y Ephraim","year":"1985","unstructured":"Ephraim, Y., & Malah, D. (1985). Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Transactions on Acoustics, Speech, and Signal Processing, 33(2), 443\u2013445.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9537_CR7","unstructured":"Fodor, B., & Fingscheidt, T. (2012). Reference-free SNR measurement for narrowband and wideband speech signals in car noise. In Proceedings of Speech Communication: ITG Symposium (pp.\u00a01\u20134). VDE."},{"key":"9537_CR8","volume-title":"Digital speech processing synthesis, and recognition","author":"S Furui","year":"1989","unstructured":"Furui, S. (1989). Digital speech processing synthesis, and recognition. New York: Marcel Dekker."},{"key":"9537_CR9","volume-title":"Timit acoustic-phonetic continuous speech corpus","author":"JS Garofolo","year":"1993","unstructured":"Garofolo, J. S., Lamel, L. F., Fisher, W. M., Fiscus, J. G., Pallett, D. S., Dahlgren, N. L., & Zue, V. (1993). Timit acoustic-phonetic continuous speech corpus. Philadelphia: Linguistic Data Consortium."},{"issue":"5","key":"9537_CR10","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1109\/TASL.2008.921764","volume":"16","author":"T Gerkmann","year":"2008","unstructured":"Gerkmann, T., Breithaupt, C., & Martin, R. (2008). Improved a posteriori speech presence probability estimation based on a likelihood ratio with fixed priors. IEEE Transactions on Audio, Speech, and Language Processing, 16(5), 910\u2013919.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9537_CR11","doi-asserted-by":"crossref","unstructured":"Hansen, J. H., & Pellom, B. L. (1998). An effective quality evaluation protocol for speech enhancement algorithms. In Fifth International Conference on Spoken Language Processing.","DOI":"10.21437\/ICSLP.1998-350"},{"key":"9537_CR12","doi-asserted-by":"crossref","unstructured":"Hirsch, H. G., & Ehrlicher, C. (1995). Noise estimation techniques for robust speech recognition. In International Conference on Acoustics, Speech, and Signal Processing ICASSP-95. (Vol.\u00a01, pp.\u00a0153\u2013156). IEEE.","DOI":"10.1109\/ICASSP.1995.479387"},{"issue":"2","key":"9537_CR13","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.1121\/1.2939132","volume":"124","author":"G Hu","year":"2008","unstructured":"Hu, G., & Wang, D. (2008). Segregation of unvoiced speech from nonspeech interference. The Journal of the Acoustical Society of America, 124(2), 1306\u20131319.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"7\u20138","key":"9537_CR14","doi-asserted-by":"publisher","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 Communication, 49(7\u20138), 588\u2013601.","journal-title":"Speech Communication"},{"key":"9537_CR15","doi-asserted-by":"crossref","unstructured":"Kim, C., & Stern, R. M. (2008). Robust signal-to-noise ratio estimation based on waveform amplitude distribution analysis. In Ninth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2008-644"},{"issue":"1","key":"9537_CR16","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.specom.2009.08.009","volume":"52","author":"T Kinnunen","year":"2010","unstructured":"Kinnunen, T., & Li, H. (2010). An overview of text-independent speaker recognition: From features to supervectors. Speech Communication, 52(1), 12\u201340.","journal-title":"Speech Communication"},{"issue":"7","key":"9537_CR17","doi-asserted-by":"publisher","first-page":"354850","DOI":"10.1155\/ASP.2005.1110","volume":"2005","author":"T Lotter","year":"2005","unstructured":"Lotter, T., & Vary, P. (2005). Speech enhancement by MAP spectral amplitude estimation using a super-Gaussian speech model. EURASIP Journal on Advances in Signal Processing, 2005(7), 354850.","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"9537_CR18","doi-asserted-by":"crossref","unstructured":"Manam, A. B., Revanth, T. S., Das, R. K., & Prasanna, S. M. (2016). Speaker verification using acoustic factor analysis with phonetic content compensation in limited and degraded test conditions. In Region 10 Conference (TENCON), 2016 IEEE (pp.\u00a01402\u20131406). IEEE.","DOI":"10.1109\/TENCON.2016.7848245"},{"key":"9537_CR19","doi-asserted-by":"crossref","unstructured":"Martin, R. (1993). An efficient algorithm to estimate the instantaneous SNR of speech signals. In Third European Conference on Speech Communication and Technology.","DOI":"10.21437\/Eurospeech.1993-270"},{"issue":"5","key":"9537_CR20","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/89.928915","volume":"9","author":"R Martin","year":"2001","unstructured":"Martin, R. (2001). Noise power spectral density estimation based on optimal smoothing and minimum statistics. IEEE Transactions on Speech and Audio Processing, 9(5), 504\u2013512.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"12","key":"9537_CR21","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1049\/el.2012.0799","volume":"48","author":"T Moazzeni","year":"2012","unstructured":"Moazzeni, T., Amei, A., Ma, J., & Jiang, Y. (2012). Statistical model based SNR estimation method for speech signals. Electronics Letters, 48(12), 727\u2013729.","journal-title":"Electronics Letters"},{"key":"9537_CR22","doi-asserted-by":"crossref","unstructured":"Morales-Cordovilla, J. A., Ma, N., S\u00e1nchez, V., Carmona, J. L., Peinado, A. M., & Barker, J. (2011). A pitch based noise estimation technique for robust speech recognition with missing data. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp.\u00a04808\u20134811). IEEE.","DOI":"10.1109\/ICASSP.2011.5947431"},{"issue":"6","key":"9537_CR23","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1109\/LSP.2009.2016829","volume":"16","author":"KSR Murty","year":"2009","unstructured":"Murty, K. S. R., Yegnanarayana, B., & Joseph, M. A. (2009). Characterization of glottal activity from speech signals. IEEE Signal Processing Letters, 16(6), 469\u2013472.","journal-title":"IEEE Signal Processing Letters"},{"issue":"9","key":"9537_CR24","doi-asserted-by":"publisher","first-page":"2518","DOI":"10.1109\/TASL.2012.2205242","volume":"20","author":"A Narayanan","year":"2012","unstructured":"Narayanan, A., & Wang, D. (2012). A CASA-based system for long-term SNR estimation. IEEE Transactions on Audio, Speech, and Language Processing, 20(9), 2518\u20132527.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"2","key":"9537_CR25","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1109\/TCOM.1972.1091123","volume":"20","author":"M Paez","year":"1972","unstructured":"Paez, M., & Glisson, T. (1972). Minimum mean-squared-error quantization in speech PCM and DPCM systems. IEEE Transactions on Communications, 20(2), 225\u2013230.","journal-title":"IEEE Transactions on Communications"},{"issue":"12","key":"9537_CR26","doi-asserted-by":"publisher","first-page":"2495","DOI":"10.1109\/TASLP.2016.2615240","volume":"24","author":"P Papadopoulos","year":"2016","unstructured":"Papadopoulos, P., Tsiartas, A., & Narayanan, S. (2016). Long-term SNR estimation of speech signals in known and unknown channel conditions. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 24(12), 2495\u20132506.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"6","key":"9537_CR27","doi-asserted-by":"publisher","first-page":"2098","DOI":"10.1109\/TASL.2006.872621","volume":"14","author":"C Plapous","year":"2006","unstructured":"Plapous, C., Marro, C., & Scalart, P. (2006). Improved signal-to-noise ratio estimation for speech enhancement. IEEE Transactions on Audio, Speech, and Language Processing, 14(6), 2098\u20132108.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"9537_CR28","first-page":"6","volume":"14","author":"P Pollak","year":"2005","unstructured":"Pollak, P., & Vondrasek, M. (2005). Methods for speech SNR estimation&58: Evaluation tool and analysis of VAD dependency. Radioengineering, 14(1), 6\u201311.","journal-title":"Radioengineering"},{"key":"9537_CR29","volume-title":"Digital processing of speech signals","author":"LR Rabiner","year":"1978","unstructured":"Rabiner, L. R., & Schafer, R. W. (1978). Digital processing of speech signals. Upper Saddle River: Prentice Hall."},{"key":"9537_CR30","doi-asserted-by":"crossref","unstructured":"Ren, Y., & Johnson, M. T. (2008). An improved SNR estimator for speech enhancement. In IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP. (pp.\u00a04901\u20134904). IEEE.","DOI":"10.1109\/ICASSP.2008.4518756"},{"issue":"3","key":"9537_CR31","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1007\/s10772-016-9336-6","volume":"19","author":"P Saha","year":"2016","unstructured":"Saha, P., Baruah, U., Laskar, R. H., Mishra, S., Choudhury, S. P., & Das, T. K. (2016). Robust analysis for improvement of vowel onset point detection under noisy conditions. International Journal of Speech Technology, 19(3), 433\u2013448.","journal-title":"International Journal of Speech Technology"},{"key":"9537_CR32","doi-asserted-by":"crossref","unstructured":"Scalart, P. (1996). Speech enhancement based on a priori signal to noise estimation. In IEEE International Conference on Acoustics, Speech, and Signal Processing (Vol.\u00a02, pp.\u00a0629\u2013632). IEEE.","DOI":"10.1109\/ICASSP.1996.543199"},{"issue":"1","key":"9537_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/97.736233","volume":"6","author":"J Sohn","year":"1999","unstructured":"Sohn, J., Kim, N. S., & Sung, W. (1999). A statistical model-based voice activity detection. IEEE Signal Processing Letters, 6(1), 1\u20133.","journal-title":"IEEE Signal Processing Letters"},{"issue":"1","key":"9537_CR34","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1109\/TASL.2010.2045799","volume":"19","author":"S Suhadi","year":"2011","unstructured":"Suhadi, S., Last, C., & Fingscheidt, T. (2011). A data-driven approach to a priori SNR estimation. IEEE Transactions on Audio, Speech, and Language Processing, 19(1), 186\u2013195.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"9537_CR35","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1109\/TSA.2003.811542","volume":"11","author":"J Tchorz","year":"2003","unstructured":"Tchorz, J., & Kollmeier, B. (2003). SNR estimation based on amplitude modulation analysis with applications to noise suppression. IEEE Transactions on Speech and Audio Processing, 11(3), 184\u2013192.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9537_CR36","unstructured":"The NIST Speech, SNR Measurement [Online]. http:\/\/www.nist.gov\/smartspace\/nistspeechsnrmeasurement.html ."},{"key":"9537_CR37","unstructured":"Varga, A., Steenneken, H. J. M., Tomlinson, M., & Jones, D. (1992). The NOISEX-92 study on the effect of additive noise on automatic speech recognition, 1992. Documentation included in the NOISEX-92 CD-ROMs."},{"key":"9537_CR38","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/0-387-22794-6_12","volume-title":"Speech separation by humans and machines","author":"D Wang","year":"2005","unstructured":"Wang, D. (2005). Speech separation by humans and machines (pp.\u00a0181\u2013197). Boston: Springer."},{"key":"9537_CR39","doi-asserted-by":"crossref","unstructured":"Zhao, X., Shao, Y., & Wang, D. (2011). Robust speaker identification using a CASA front-end. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (pp.\u00a05468\u20135471). IEEE","DOI":"10.1109\/ICASSP.2011.5947596"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9537-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-018-9537-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9537-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T11:26:32Z","timestamp":1720524392000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-018-9537-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,20]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["9537"],"URL":"https:\/\/doi.org\/10.1007\/s10772-018-9537-2","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8,20]]},"assertion":[{"value":"27 February 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}