{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:43:49Z","timestamp":1774421029899,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2021,7,31]],"date-time":"2021-07-31T00:00:00Z","timestamp":1627689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,31]],"date-time":"2021-07-31T00:00:00Z","timestamp":1627689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100006769","name":"Russian Science Foundation","doi-asserted-by":"crossref","award":["20-71-10010"],"award-info":[{"award-number":["20-71-10010"]}],"id":[{"id":"10.13039\/501100006769","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100007675","name":"Laboratory of Algorithms and Technologies for Networks Analysis","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007675","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Optim Lett"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s11590-021-01790-5","type":"journal-article","created":{"date-parts":[[2021,7,31]],"date-time":"2021-07-31T18:02:48Z","timestamp":1627754568000},"page":"2095-2113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Gain-optimized spectral distortions for pronunciation training"],"prefix":"10.1007","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6196-0564","authenticated-orcid":false,"given":"Andrey V.","family":"Savchenko","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3045-3337","authenticated-orcid":false,"given":"Vladimir V.","family":"Savchenko","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2776-5471","authenticated-orcid":false,"given":"Lyudmila V.","family":"Savchenko","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,31]]},"reference":[{"issue":"6","key":"1790_CR1","doi-asserted-by":"publisher","first-page":"3731","DOI":"10.1007\/s10639-019-09955-7","volume":"24","author":"C Agarwal","year":"2019","unstructured":"Agarwal, C., Chakraborty, P.: A review of tools and techniques for computer aided pronunciation training (CAPT) in English. Educ. Inf. Technol. 24(6), 3731\u20133743 (2019)","journal-title":"Educ. Inf. Technol."},{"issue":"3","key":"1790_CR2","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1016\/j.specom.2009.11.001","volume":"52","author":"JP Arias","year":"2010","unstructured":"Arias, J.P., Yoma, N.B., Vivanco, H.: Automatic intonation assessment for computer aided language learning. Speech Commun. 52(3), 254\u2013267 (2010)","journal-title":"Speech Commun."},{"key":"1790_CR3","unstructured":"Bastos, I., Oliveira, L.B., Goes, J., Silva, M.: MOSFET-only wideband LNA with noise cancelling and gain optimization. In: Proceedings of the 17th International Conference Mixed Design of Integrated Circuits and Systems (MIXDES), pp. 306\u2013311. IEEE (2010)"},{"key":"1790_CR4","volume-title":"Springer Handbook of Speech Processing","author":"J Benesty","year":"2007","unstructured":"Benesty, J., Sondhi, M.M., Huang, Y.: Springer Handbook of Speech Processing. Springer, Berlin (2007)"},{"key":"1790_CR5","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.specom.2019.10.005","volume":"115","author":"S Ding","year":"2019","unstructured":"Ding, S., Liberatore, C., Sonsaat, S., Lu\u010di\u0107, I., Silpachai, A., Zhao, G., Chukharev-Hudilainen, E., Levis, J., Gutierrez-Osuna, R.: Golden speaker builder-an interactive tool for pronunciation training. Speech Commun. 115, 51\u201366 (2019)","journal-title":"Speech Commun."},{"key":"1790_CR6","doi-asserted-by":"crossref","unstructured":"Dionelis, N., Brookes, M.: Speech enhancement using modulation-domain Kalman filtering with active speech level normalized log-spectrum global priors. In: Proceedings of the 25th European Signal Processing Conference (EUSIPCO), pp. 2309\u20132313. IEEE (2017)","DOI":"10.23919\/EUSIPCO.2017.8081622"},{"key":"1790_CR7","doi-asserted-by":"crossref","unstructured":"Elaraby, M.S., Abdallah, M., Abdou, S., Rashwan, M.: A deep neural networks (DNN) based models for a computer aided pronunciation learning system. In: International Conference on Speech and Computer (SPECOM), pp. 51\u201358. Springer (2016)","DOI":"10.1007\/978-3-319-43958-7_5"},{"issue":"7\u20138","key":"1790_CR8","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1016\/j.specom.2006.06.012","volume":"49","author":"J Erkelens","year":"2007","unstructured":"Erkelens, J., Jensen, J., Heusdens, R.: A data-driven approach to optimizing spectral speech enhancement methods for various error criteria. Speech Commun. 49(7\u20138), 530\u2013541 (2007)","journal-title":"Speech Commun."},{"issue":"3","key":"1790_CR9","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1177\/0265532210364408","volume":"27","author":"H Franco","year":"2010","unstructured":"Franco, H., Bratt, H., Rossier, R., Rao Gadde, V., Shriberg, E., Abrash, V., Precoda, K.: Eduspeak\u00ae: a speech recognition and pronunciation scoring toolkit for computer-aided language learning applications. Language Test. 27(3), 401\u2013418 (2010)","journal-title":"Language Test."},{"issue":"1","key":"1790_CR10","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1080\/09588221.2012.700315","volume":"27","author":"EM Golonka","year":"2014","unstructured":"Golonka, E.M., Bowles, A.R., Frank, V.M., Richardson, D.L., Freynik, S.: Technologies for foreign language learning: a review of technology types and their effectiveness. Comput. Assisted Language Learn. 27(1), 70\u2013105 (2014)","journal-title":"Comput. Assisted Language Learn."},{"key":"1790_CR11","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep learning. MIT press, Cambridge (2016)"},{"issue":"4","key":"1790_CR12","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1109\/TASSP.1980.1163421","volume":"28","author":"R Gray","year":"1980","unstructured":"Gray, R., Buzo, A., Gray, A., Matsuyama, Y.: Distortion measures for speech processing. IEEE Trans. Acoustics Speech Signal Process. 28(4), 367\u2013376 (1980)","journal-title":"IEEE Trans. Acoustics Speech Signal Process."},{"key":"1790_CR13","doi-asserted-by":"crossref","unstructured":"Haikun, T., Shiying, W., Xinsheng, L., Yue, X.G.: Speech recognition model based on deep learning and application in pronunciation quality evaluation system. In: Proceedings of the International Conference on Data Mining and Machine Learning, pp. 1\u20135 (2019)","DOI":"10.1145\/3335656.3335657"},{"key":"1790_CR14","doi-asserted-by":"crossref","unstructured":"Han, K.I., Park, H.J., Lee, K.M.: Speech recognition and lip shape feature extraction for English vowel pronunciation of the hearing-impaired based on SVM technique. In: Proceedings of the International Conference on Big Data and Smart Computing (BigComp), pp. 293\u2013296. IEEE (2016)","DOI":"10.1109\/BIGCOMP.2016.7425931"},{"key":"1790_CR15","doi-asserted-by":"crossref","unstructured":"Hu, W., Qian, Y., Soong, F.K.: A new DNN-based high quality pronunciation evaluation for computer-aided language learning (CALL). In: Proceedings of Interspeech, pp. 1886\u20131890 (2013)","DOI":"10.21437\/Interspeech.2013-458"},{"key":"1790_CR16","doi-asserted-by":"crossref","unstructured":"Huang, G., Ye, J., Shen, Y., Zhou, Y.: A evaluating model of English pronunciation for Chinese students. In: Proceedings of the 9th International Conference on Communication Software and Networks (ICCSN), pp. 1062\u20131065. IEEE (2017)","DOI":"10.1109\/ICCSN.2017.8230273"},{"key":"1790_CR17","unstructured":"Itakura, F., Saito, S.: Analysis synthesis telephony based on the maximum likelihood method. In: Proceedings of the 6th International Congress on Acoustics, pp. 17\u201320 (1968)"},{"key":"1790_CR18","unstructured":"Kneller, E., Karaulnyh, D.: System and method of converting voice signal into transcript presentation with metadata (2016). RU Patent 2589851 C2"},{"key":"1790_CR19","volume-title":"Information Theory and Statistics","author":"S Kullback","year":"1997","unstructured":"Kullback, S.: Information Theory and Statistics. Dover Publications, New York (1997)"},{"key":"1790_CR20","volume-title":"Digital Spectral Analysis with Applications","author":"SL Marple Jr","year":"2019","unstructured":"Marple, S.L., Jr.: Digital Spectral Analysis with Applications, 2nd edn. Courier Dover Publications, New York (2019)","edition":"2"},{"key":"1790_CR21","doi-asserted-by":"crossref","unstructured":"Mo\u0161ner, L., Wu, M., Raju, A., Parthasarathi, S.H.K., Kumatani, K., Sundaram, S., Maas, R., Hoffmeister, B.: Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6475\u20136479. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683422"},{"key":"1790_CR22","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.patrec.2015.07.013","volume":"65","author":"AV Savchenko","year":"2015","unstructured":"Savchenko, A.V., Savchenko, L.V.: Towards the creation of reliable voice control system based on a fuzzy approach. Pattern Recogn. Letts. 65, 145\u2013151 (2015)","journal-title":"Pattern Recogn. Letts."},{"key":"1790_CR23","doi-asserted-by":"crossref","unstructured":"Savchenko, A.V., Savchenko, V.V., Savchenko, L.V.: Optimization of gain in symmetrized itakura-saito discrimination for pronunciation learning. In: Proceedings of International Conference on Mathematical Optimization Theory and Operations Research (MOTOR), pp. 440\u2013454. Springer (2020)","DOI":"10.1007\/978-3-030-49988-4_30"},{"key":"1790_CR24","doi-asserted-by":"crossref","unstructured":"Savchenko, L.V., Savchenko, A.V.: Fuzzy phonetic decoding method in a phoneme recognition problem. In: International Conference on Nonlinear Speech Processing (NOLISP), pp. 176\u2013183. Springer (2013)","DOI":"10.1007\/978-3-642-38847-7_23"},{"issue":"1","key":"1790_CR25","doi-asserted-by":"publisher","first-page":"42","DOI":"10.3103\/S0735272720010045","volume":"63","author":"VV Savchenko","year":"2020","unstructured":"Savchenko, V.V.: Minimum of information divergence criterion for signals with tuning to speaker voice in automatic speech recognition. Radioelectron. Commun. Syst. 63(1), 42\u201354 (2020)","journal-title":"Radioelectron. Commun. Syst."},{"issue":"9","key":"1790_CR26","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1007\/s11018-019-01702-1","volume":"62","author":"VV Savchenko","year":"2019","unstructured":"Savchenko, V.V., Savchenko, L.V.: Method for measuring the intelligibility of speech signals in the Kullback-Leibler information metric. Measurement Tech. 62(9), 832\u2013839 (2019)","journal-title":"Measurement Tech."},{"key":"1790_CR27","doi-asserted-by":"crossref","unstructured":"Srinivasan, A., Yarra, C., Ghosh, P.K.: Automatic assessment of pronunciation and its dependent factors by exploring their interdependencies using DNN and LSTM. In: Proceedings of the 8th ISCA Workshop on Speech and Language Technology in Education (SLaTE), pp. 30\u201334 (2019)","DOI":"10.21437\/SLaTE.2019-7"},{"key":"1790_CR28","unstructured":"Su, H.Y., Gao, Y.: Adaptive gain reduction for encoding a speech signal (2016). US Patent 9,269,365"},{"key":"1790_CR29","doi-asserted-by":"crossref","unstructured":"Sudhakara, S., Ramanathi, M.K., Yarra, C., Ghosh, P.K.: An improved goodness of pronunciation (GoP) measure for pronunciation evaluation with DNN-HMM system considering hmm transition probabilities. Proceedings of Interspeech. pp. 954\u2013958 (2019)","DOI":"10.21437\/Interspeech.2019-2363"},{"key":"1790_CR30","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.csl.2017.12.010","volume":"50","author":"D Sztah\u00f3","year":"2018","unstructured":"Sztah\u00f3, D., Kiss, G., Vicsi, K.: Computer based speech prosody teaching system. Comput Speech Language 50, 126\u2013140 (2018)","journal-title":"Comput Speech Language"},{"key":"1790_CR31","doi-asserted-by":"crossref","unstructured":"Tejedor-Garc\u00eda, C., Escudero, D., C\u00e1mara-Arenas, E., Gonz\u00e1lez-Ferreras, C., Carde\u00f1oso-Payo, V.: Assessing pronunciation improvement in students of english using a controlled computer-assisted pronunciation tool. IEEE Transactions on Learning Technologies (2020)","DOI":"10.1109\/TLT.2020.2980261"},{"key":"1790_CR32","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Soong, F., Hu, W.: Paired phone-posteriors approach to ESL pronunciation quality assessment. Proceedings of Interspeech pp. 1631\u20131635 (2018)","DOI":"10.21437\/Interspeech.2018-1270"},{"key":"1790_CR33","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.specom.2021.04.004","volume":"130","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., Wang, Y., Yang, J.: Text-conditioned transformer for automatic pronunciation error detection. Speech Commun. 130, 55\u201363 (2021)","journal-title":"Speech Commun."}],"container-title":["Optimization Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11590-021-01790-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11590-021-01790-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11590-021-01790-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T12:14:06Z","timestamp":1659615246000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11590-021-01790-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,31]]},"references-count":33,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["1790"],"URL":"https:\/\/doi.org\/10.1007\/s11590-021-01790-5","relation":{},"ISSN":["1862-4472","1862-4480"],"issn-type":[{"value":"1862-4472","type":"print"},{"value":"1862-4480","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,31]]},"assertion":[{"value":"5 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}