{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T21:50:40Z","timestamp":1780350640456,"version":"3.54.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2016,9,27]],"date-time":"2016-09-27T00:00:00Z","timestamp":1474934400000},"content-version":"unspecified","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":[[2016,12]]},"DOI":"10.1007\/s10772-016-9369-x","type":"journal-article","created":{"date-parts":[[2016,9,27]],"date-time":"2016-09-27T06:16:25Z","timestamp":1474956985000},"page":"769-777","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A GMM\/HMM model for reconstruction of missing speech spectral components for continuous speech recognition"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1843-4037","authenticated-orcid":false,"given":"Mohammad Mohsen","family":"Goodarzi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farshad","family":"Almasganj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,27]]},"reference":[{"key":"9369_CR1","unstructured":"Bijankhan, M., Sheikhzadegan, J., Roohani, M. R., Samareh, Y., Lucas, C., & Tebyani, M. (1994). FARSDAT\u2014The speech data base of Farsi spoken language. In International conference on speech science and technology (SST) (pp. 826\u2013831). Perth."},{"key":"9369_CR2","doi-asserted-by":"crossref","unstructured":"Borgstr\u00d6m, B. J., & Alwan, A. (2009). Utilizing compressibility in reconstructing spectrographic data, with applications to noise robust ASR. IEEE Signal Processing Letters, 16(5), 398\u2013401. Retrieved July 21, 2012 from http:\/\/ieeexplore.ieee.org\/xpl\/articleDetails.jsp?tp=&arnumber=4804947&contentType=Journals+&+Magazines&sortType=asc_p_Sequence&filter=AND(p_IS_Number:4802157)","DOI":"10.1109\/LSP.2009.2016452"},{"issue":"6","key":"9369_CR3","doi-asserted-by":"publisher","first-page":"1612","DOI":"10.1109\/TASL.2009.2038811","volume":"18","author":"BJ Borgstr\u00f6m","year":"2010","unstructured":"Borgstr\u00f6m, B. J., & Alwan, A. (2010). HMM-based reconstruction of unreliable spectrographic data for noise robust speech recognition. IEEE Transactions on Audio, Speech and Language Processing, 18(6), 1612\u20131623. doi: 10.1109\/TASL.2009.2038811 .","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"3","key":"9369_CR4","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/j.csl.2006.08.001","volume":"21","author":"C Cerisara","year":"2007","unstructured":"Cerisara, C., Demange, S., & Haton, J.-P. (2007). On noise masking for automatic missing data speech recognition: A survey and discussion. Computer Speech & Language, 21(3), 443\u2013457. doi: 10.1016\/j.csl.2006.08.001 .","journal-title":"Computer Speech & Language"},{"key":"9369_CR5","doi-asserted-by":"publisher","unstructured":"Chiu, Y. -H. B., & Stern, R. M. (2009). Minimum variance modulation filter for robust speech recognition. In 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 3917\u20133920). IEEE. doi: 10.1109\/ICASSP.2009.4960484","DOI":"10.1109\/ICASSP.2009.4960484"},{"key":"9369_CR6","doi-asserted-by":"crossref","unstructured":"Cooke, M., Green, P., & Crawford, M. (1994). Handling missing data in speech recognition. In International conference on spoken language processing. Yokahama. doi:10.1.1.45.3451","DOI":"10.21437\/ICSLP.1994-403"},{"key":"9369_CR7","doi-asserted-by":"crossref","unstructured":"Cooke, M., Green, P., Josifovski, L., & Vizinho, A. (2001). Robust automatic speech recognition with missing and unreliable acoustic data. Speech Communication, 34, 267\u2013285. Retrieved September 17, 2012 from http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.130.6933","DOI":"10.1016\/S0167-6393(00)00034-0"},{"key":"9369_CR8","doi-asserted-by":"crossref","unstructured":"Demange, S., Cerisara, C., & Haton, J. -P. (2009). Missing data mask estimation with frequency and temporal dependencies. Computer Speech & Language, 23(1), 25\u201341. Retrieved December 3, 2013 from http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0885230808000053","DOI":"10.1016\/j.csl.2008.02.002"},{"issue":"2","key":"9369_CR9","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1016\/j.csl.2010.06.004","volume":"25","author":"JF Gemmeke","year":"2011","unstructured":"Gemmeke, J. F., Cranen, B., & Remes, U. (2011). Sparse imputation for large vocabulary noise robust ASR. Computer Speech & Language, 25(2), 462\u2013479. doi: 10.1016\/j.csl.2010.06.004 .","journal-title":"Computer Speech & Language"},{"key":"9369_CR10","unstructured":"Gillian, M. D. (2002). Noise reduction in speech applications (electrical engineering & applied signal processing series). Maryland: CRC Press. Retrieved September 17, 2012 from http:\/\/www.amazon.com\/Reduction-Applications-Electrical-Engineering-Processing\/dp\/0849309492"},{"issue":"3","key":"9369_CR11","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1109\/TASL.2012.2229982","volume":"21","author":"JA Gonzalez","year":"2013","unstructured":"Gonzalez, J. A., Peinado, A. M., Ma, N., Gomez, A. M., & Barker, J. (2013). MMSE-based missing-feature reconstruction with temporal modeling for robust speech recognition. IEEE Transactions on Audio, Speech and Language Processing, 21(3), 624\u2013635. doi: 10.1109\/TASL.2012.2229982 .","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9369_CR12","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.compeleceng.2015.07.013","volume":"46","author":"MM Goodarzi","year":"2015","unstructured":"Goodarzi, M. M., & Almasganj, F. (2015). Joint sparsity and marginal classification for improving sparse imputation performance in speech recognition. Computers & Electrical Engineering, 46, 56\u201364. doi: 10.1016\/j.compeleceng.2015.07.013 .","journal-title":"Computers & Electrical Engineering"},{"key":"9369_CR13","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1016\/j.specom.2015.06.009","volume":"76","author":"MM Goodarzi","year":"2016","unstructured":"Goodarzi, M. M., & Almasganj, F. (2016). Model-based clustered sparse imputation for noise robust speech recognition. Speech Communication, 76, 218\u2013229. doi: 10.1016\/j.specom.2015.06.009 .","journal-title":"Speech Communication"},{"key":"9369_CR14","doi-asserted-by":"publisher","unstructured":"Goodarzi, M. M., Almasganj, F., & Ahadi, M. (2010). Reconstructing missing speech spectral components using both temporal and statistical correlations. In 10th International conference on information science, signal processing and their applications (ISSPA 2010) (pp. 125\u2013128). IEEE. doi: 10.1109\/ISSPA.2010.5605492","DOI":"10.1109\/ISSPA.2010.5605492"},{"issue":"4","key":"9369_CR15","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1007\/s10772-014-9233-9","volume":"17","author":"JHL Hansen","year":"2014","unstructured":"Hansen, J. H. L., Kumar, A., & Angkititrakul, P. (2014). Environment mismatch compensation using average eigenspace-based methods for robust speech recognition. International Journal of Speech Technology, 17(4), 353\u2013364. doi: 10.1007\/s10772-014-9233-9 .","journal-title":"International Journal of Speech Technology"},{"issue":"5","key":"9369_CR16","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.1109\/JPROC.2012.2236871","volume":"101","author":"H Hermansky","year":"2013","unstructured":"Hermansky, H. (2013). Multistream recognition of speech: Dealing with unknown unknowns. Proceedings of the IEEE, 101(5), 1076\u20131088. doi: 10.1109\/JPROC.2012.2236871 .","journal-title":"Proceedings of the IEEE"},{"issue":"2","key":"9369_CR17","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1109\/TASLP.2013.2292328","volume":"22","author":"H Kallasjoki","year":"2014","unstructured":"Kallasjoki, H., Gemmeke, J. F., & Palomaki, K. J. (2014). Estimating uncertainty to improve exemplar-based feature enhancement for noise robust speech recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 22(2), 368\u2013380. doi: 10.1109\/TASLP.2013.2292328 .","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"9369_CR18","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1016\/j.csl.2012.06.005","volume":"27","author":"S Keronen","year":"2013","unstructured":"Keronen, S., Kallasjoki, H., Remes, U., Brown, G. J., Gemmeke, J. F., & Palom\u00e4ki, K. J. (2013). Mask estimation and imputation methods for missing data speech recognition in a multisource reverberant environment. Computer Speech & Language, 27(3), 798\u2013819. doi: 10.1016\/j.csl.2012.06.005 .","journal-title":"Computer Speech & Language"},{"issue":"2","key":"9369_CR19","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1109\/TASL.2010.2048604","volume":"19","author":"M Kuhne","year":"2011","unstructured":"Kuhne, M., Togneri, R., & Nordholm, S. (2011). A new evidence model for missing data speech recognition with applications in reverberant multi-source environments. IEEE Transactions on Audio, Speech and Language Processing, 19(2), 372\u2013384. doi: 10.1109\/TASL.2010.2048604 .","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9369_CR20","doi-asserted-by":"publisher","unstructured":"Luan, Y., Saito, D., Kashiwagi, Y., Minematsu, N., & Hirose, K. (2014). Semi-supervised noise dictionary adaptation for exemplar-based noise robust speech recognition. In 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 1745\u20131748). IEEE. doi: 10.1109\/ICASSP.2014.6853897","DOI":"10.1109\/ICASSP.2014.6853897"},{"key":"9369_CR21","unstructured":"Ma, N., & Barker, J. (2013). A fragment-decoding plus missing-data imputation ASR system evaluated on the 2nd CHiME Challenge. In The 2nd CHiME workshop on machine listening in multisource environments. Vancouver."},{"issue":"4","key":"9369_CR22","doi-asserted-by":"publisher","first-page":"3918","DOI":"10.1016\/j.eswa.2010.09.053","volume":"38","author":"A Mohammadi","year":"2011","unstructured":"Mohammadi, A., & Almasganj, F. (2011). Reconstruction of missing features by means of multivariate Laplace distribution (MLD) for noise robust speech recognition. Expert Systems with Applications, 38(4), 3918\u20133930. doi: 10.1016\/j.eswa.2010.09.053 .","journal-title":"Expert Systems with Applications"},{"key":"9369_CR23","doi-asserted-by":"publisher","unstructured":"Mohammadi, A., Almasganj, F., Taherkhani, A., & Naderkhani, F. (2007). Using phoneme segmentation in conjunction with missing feature approaches for noise robust speech recognition. In 2007 IEEE international symposium on signal processing and information technology (pp. 297\u2013301). IEEE. doi: 10.1109\/ISSPIT.2007.4458075","DOI":"10.1109\/ISSPIT.2007.4458075"},{"issue":"8","key":"9369_CR24","doi-asserted-by":"publisher","first-page":"2101","DOI":"10.1016\/j.sigpro.2011.03.020","volume":"91","author":"I Mporas","year":"2011","unstructured":"Mporas, I., Ganchev, T., Kocsis, O., & Fakotakis, N. (2011). Context-adaptive pre-processing scheme for robust speech recognition in fast-varying noise environment. Signal Processing, 91(8), 2101\u20132111. doi: 10.1016\/j.sigpro.2011.03.020 .","journal-title":"Signal Processing"},{"issue":"2","key":"9369_CR25","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257\u2013286. doi: 10.1109\/5.18626 .","journal-title":"Proceedings of the IEEE"},{"issue":"4","key":"9369_CR26","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1016\/j.specom.2004.03.007","volume":"43","author":"B Raj","year":"2004","unstructured":"Raj, B., Seltzer, M. L., & Stern, R. M. (2004). Reconstruction of missing features for robust speech recognition. Speech Communication, 43(4), 275\u2013296. doi: 10.1016\/j.specom.2004.03.007 .","journal-title":"Speech Communication"},{"issue":"5","key":"9369_CR27","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1109\/MSP.2005.1511828","volume":"22","author":"B Raj","year":"2005","unstructured":"Raj, B., & Stern, R. M. (2005). Missing-feature approaches in speech recognition. IEEE Signal Processing Magazine, 22(5), 101\u2013116. doi: 10.1109\/MSP.2005.1511828 .","journal-title":"IEEE Signal Processing Magazine"},{"issue":"6","key":"9369_CR28","doi-asserted-by":"publisher","first-page":"1923","DOI":"10.1016\/j.dsp.2013.06.011","volume":"23","author":"Y Shekofteh","year":"2013","unstructured":"Shekofteh, Y., & Almasganj, F. (2013). Autoregressive modeling of speech trajectory transformed to the reconstructed phase space for ASR purposes. Digital Signal Processing, 23(6), 1923\u20131932. doi: 10.1016\/j.dsp.2013.06.011 .","journal-title":"Digital Signal Processing"},{"issue":"8","key":"9369_CR29","doi-asserted-by":"publisher","first-page":"2418","DOI":"10.1109\/TASL.2011.2136337","volume":"19","author":"QF Tan","year":"2011","unstructured":"Tan, Q. F., Georgiou, P. G., & Narayanan, S. (2011). Enhanced sparse imputation techniques for a robust speech recognition front-end. IEEE Transactions on Audio, Speech and Language Processing, 19(8), 2418\u20132429. doi: 10.1109\/TASL.2011.2136337 .","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"3","key":"9369_CR30","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga, A., & Steeneken, H. J. M. (1993). Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems. Speech Communication, 12(3), 247\u2013251. doi: 10.1016\/0167-6393(93)90095-3 .","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\/s10772-016-9369-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-016-9369-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9369-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T16:15:45Z","timestamp":1718813745000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-016-9369-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,9,27]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["9369"],"URL":"https:\/\/doi.org\/10.1007\/s10772-016-9369-x","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,9,27]]}}}