{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T21:24:47Z","timestamp":1781731487393,"version":"3.54.5"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T00:00:00Z","timestamp":1704499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T00:00:00Z","timestamp":1704499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s10772-023-10078-1","type":"journal-article","created":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T10:02:03Z","timestamp":1704535323000},"page":"77-84","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Advancements in encoded speech data by background noise suppression under uncontrolled environment"],"prefix":"10.1007","volume":"27","author":[{"given":"B. G.","family":"Nagaraja","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3266-9732","authenticated-orcid":false,"given":"G. Thimmaraja","family":"Yadava","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Anees","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,6]]},"reference":[{"key":"10078_CR1","doi-asserted-by":"crossref","unstructured":"Davidson, G., Vinton, M., Ekstrand, P., Zhou, C., Villemoes, L., & Lu, L. (2023). High quality audio coding with Mdctnet. In IEEE international conference on acoustics, speech and signal processing (pp. 1\u20135)","DOI":"10.1109\/ICASSP49357.2023.10096056"},{"issue":"6","key":"10078_CR2","first-page":"1109","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 Audio, Speech, and Language Processing, 32(6), 1109\u20131121.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"10078_CR3","doi-asserted-by":"crossref","unstructured":"G\u00e2rbacea, C., van den Oord, A., Li, Y., Lim, F.S., Luebs, A., Vinyals, O., & Walters, T.C. (2019). Low bit-rate speech coding with VQ-VAE and a WaveNet decoder. In ICASSP 2019\u20132019 IEEE international conference on acoustics, speech and signal processing (pp. 735\u2013739)","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"10078_CR4","unstructured":"Hirsch, H.G., & Pearce, D. (2000). The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In ASR2000-automatic speech recognition: Challenges for the new Millenium ISCA tutorial and research workshop (ITRW)"},{"issue":"7\u20138","key":"10078_CR5","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"},{"issue":"1","key":"10078_CR7","doi-asserted-by":"publisher","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"},{"issue":"5","key":"10078_CR8","first-page":"1123","volume":"19","author":"Y Hu","year":"2010","unstructured":"Hu, Y., & Loizou, P. C. (2010). Estimators of the magnitude-squared spectrum and methods for incorporating SNR uncertainty. IEEE Transactions on Audio, Speech, and Language Processing, 19(5), 1123\u20131137.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"10078_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1504\/IJSISE.2020.113552","volume":"12","author":"SJ Jainar","year":"2020","unstructured":"Jainar, S. J., Sale, P. L., & Nagaraja, B. G. (2020). VAD, feature extraction and modelling techniques for speaker recognition: A review. International Journal of Signal and Imaging Systems Engineering, 12(1), 1\u201318.","journal-title":"International Journal of Signal and Imaging Systems Engineering"},{"key":"10078_CR10","doi-asserted-by":"crossref","unstructured":"Kankanahalli, S. (2018). End-to-end optimized speech coding with deep neural networks. In IEEE international conference on acoustics, speech and signal processing (pp. 2521\u20132525)","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"10078_CR11","doi-asserted-by":"crossref","unstructured":"Kleijn, W.B., Lim, F.S., Luebs, A., Skoglund, J., Stimberg, F., Wang, Q., & Walters, T.C. (2018) Wavenet based low rate speech coding. In IEEE international conference on acoustics, speech and signal processing (pp. 676\u2013680)","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"10078_CR12","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1007\/978-3-642-19551-8_23","volume-title":"Speech quality assessment, multimedia analysis, processing and communications","author":"PC Loizou","year":"2011","unstructured":"Loizou, P. C. (2011). Speech quality assessment, multimedia analysis, processing and communications (pp. 623\u2013654). Springer."},{"issue":"5","key":"10078_CR13","doi-asserted-by":"publisher","first-page":"3387","DOI":"10.1121\/1.3097493","volume":"125","author":"J Ma","year":"2009","unstructured":"Ma, J., Hu, Y., & Loizou, P. C. (2009). Objective measures for predicting speech intelligibility in noisy conditions based on new band-importance functions. Journal of the Acoustical Society of America, 125(5), 3387\u20133405.","journal-title":"Journal of the Acoustical Society of America"},{"issue":"3","key":"10078_CR14","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.specom.2010.10.005","volume":"53","author":"J Ma","year":"2011","unstructured":"Ma, J., & Loizou, P. C. (2011). SNR loss: A new objective measure for predicting the intelligibility of noise-suppressed speech. Speech Communication, 53(3), 340\u2013354.","journal-title":"Speech Communication"},{"issue":"6","key":"10078_CR15","doi-asserted-by":"publisher","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\u2014The 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"},{"key":"10078_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16665-3","author":"BG Nagaraja","year":"2023","unstructured":"Nagaraja, B. G., Anees, M., & Yadava, T. G. (2023). Speech coding techniques and challenges: A comprehensive literature survey. Multimedia Tools and Applications. https:\/\/doi.org\/10.1007\/s11042-023-16665-3","journal-title":"Multimedia Tools and Applications"},{"key":"10078_CR17","volume-title":"Fundamentals of speech recognition","author":"L Rabiner","year":"1993","unstructured":"Rabiner, L., & Juang, B. H. (1993). Fundamentals of speech recognition. Prentice-Hall Inc."},{"issue":"2","key":"10078_CR18","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s00530-014-0446-1","volume":"22","author":"RC Streijl","year":"2016","unstructured":"Streijl, R. C., Winkler, S., & Hands, D. S. (2016). Mean opinion score (MOS) revisited: Methods and applications, limitations and alternatives. Multimedia Systems, 22(2), 213\u2013227.","journal-title":"Multimedia Systems"},{"key":"10078_CR19","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.specom.2015.05.004","volume":"72","author":"J Tu","year":"2015","unstructured":"Tu, J., & Xia, Y. (2015). Fast distributed multichannel speech enhancement using novel frequency domain estimators of magnitude-squared spectrum. Speech Communication, 72, 96\u2013108.","journal-title":"Speech Communication"},{"issue":"1","key":"10078_CR20","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.csl.2003.12.001","volume":"19","author":"M Viswanathan","year":"2005","unstructured":"Viswanathan, M., & Viswanathan, M. (2005). Measuring speech quality for text-to-speech systems: Development and assessment of a modified mean opinion score (MOS) scale. Computer Speech & Language, 19(1), 55\u201383.","journal-title":"Computer Speech & Language"},{"issue":"5","key":"10078_CR21","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1097\/AUD.0000000000000556","volume":"39","author":"GD Watkins","year":"2018","unstructured":"Watkins, G. D., Swanson, B. A., & Suaning, G. J. (2018). An evaluation of output signal to noise ratio as a predictor of cochlear implant speech intelligibility. Ear and Hearing, 39(5), 958\u2013968.","journal-title":"Ear and Hearing"},{"key":"10078_CR22","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/s10772-020-09786-9","volume":"24","author":"TG Yadava","year":"2021","unstructured":"Yadava, T. G., Nagaraja, B. G., & Jayanna, H. S. (2021). Speech enhancement and encoding by combining SS-VAD and LPC. International Journal of Speech Technology, Springer, 24, 165\u2013172.","journal-title":"International Journal of Speech Technology, Springer"},{"issue":"17","key":"10078_CR23","doi-asserted-by":"publisher","first-page":"23633","DOI":"10.1007\/s11042-022-12152-3","volume":"81","author":"TG Yadava","year":"2022","unstructured":"Yadava, T. G., Nagaraja, B. G., & Jayanna, H. S. (2022). A spatial procedure to spectral subtraction for speech enhancement. Multimedia Tools and Applications, 81(17), 23633\u201323647.","journal-title":"Multimedia Tools and Applications"},{"issue":"7","key":"10078_CR24","doi-asserted-by":"publisher","first-page":"4041","DOI":"10.1007\/s00034-022-01973-0","volume":"41","author":"TG Yadava","year":"2022","unstructured":"Yadava, T. G., Nagaraja, B. G., & Jayanna, H. S. (2022). Enhancements in continuous Kannada ASR system by background noise elimination. Circuits, Systems, and Signal Processing, 41(7), 4041\u20134067.","journal-title":"Circuits, Systems, and Signal Processing"},{"issue":"4","key":"10078_CR25","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1109\/TASLP.2018.2887337","volume":"27","author":"Z Zhao","year":"2018","unstructured":"Zhao, Z., Liu, H., & Fingscheidt, T. (2018). Convolutional neural networks to enhance coded speech. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 27(4), 663\u2013678.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10078_CR26","doi-asserted-by":"crossref","unstructured":"Zhen, K., Sung, J., Lee, M.S., Beack, S., & Kim, M. (2019). Cascaded cross-module residual learning towards lightweight end-to-end speech coding. arXiv:1906.07769","DOI":"10.21437\/Interspeech.2019-1816"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10078-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-023-10078-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10078-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T15:10:13Z","timestamp":1715613013000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-023-10078-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,6]]},"references-count":25,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["10078"],"URL":"https:\/\/doi.org\/10.1007\/s10772-023-10078-1","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,6]]},"assertion":[{"value":"17 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2024","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 have no conflict of interest on the manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}