{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T01:03:45Z","timestamp":1782435825027,"version":"3.54.5"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,5,25]],"date-time":"2022-05-25T00:00:00Z","timestamp":1653436800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,25]],"date-time":"2022-05-25T00:00:00Z","timestamp":1653436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s10772-022-09976-7","type":"journal-article","created":{"date-parts":[[2022,5,25]],"date-time":"2022-05-25T18:03:47Z","timestamp":1653501827000},"page":"499-509","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Soft-computation based speech recognition system for Sylheti language"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1587-6924","authenticated-orcid":false,"given":"Gautam","family":"Chakraborty","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mridusmita","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Navajit","family":"Saikia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kandarpa Kumar","family":"Sarma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,25]]},"reference":[{"key":"9976_CR1","doi-asserted-by":"crossref","unstructured":"Alotaibi, Y. A., Alghamdi, M., & Alotaiby, F. (2010). Speech recognition system of Arabic alphabet based on a telephony Arabic corpus. In International conference on image and signal processing, (pp. 122\u2013129). Springer.","DOI":"10.1007\/978-3-642-13681-8_15"},{"key":"9976_CR2","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.specom.2013.07.008","volume":"56","author":"L Besacier","year":"2014","unstructured":"Besacier, L., Barnard, E., Karpov, A., & Schultz, T. (2014). Automatic speech recognition for under-resourced languages: A survey. Speech Communication, 56, 85\u2013100.","journal-title":"Speech Communication"},{"key":"9976_CR3","doi-asserted-by":"crossref","unstructured":"Bhardwaj, I., & Londhe, N. D. (2012). Hidden Markov model based isolated Hindi word recognition. In 2012 2nd International conference on power, control and embedded systems (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICPCES.2012.6508044"},{"key":"9976_CR4","first-page":"6259","volume":"8","author":"G Chakraborty","year":"2019","unstructured":"Chakraborty, G., & Saikia, N. (2019). Speech recognition of isolated words using a new speech database in sylheti. International Journal of Recent Technology and Engineering, 8, 6259\u20136268.","journal-title":"International Journal of Recent Technology and Engineering"},{"key":"9976_CR5","doi-asserted-by":"publisher","first-page":"R921","DOI":"10.1016\/j.cub.2014.08.026","volume":"24","author":"DD Cox","year":"2014","unstructured":"Cox, D. D., & Dean, T. (2014). Neural networks and neuroscience-inspired computer vision. Current Biology, 24, R921\u2013R929.","journal-title":"Current Biology"},{"key":"9976_CR6","first-page":"9","volume":"4","author":"B Deka","year":"2018","unstructured":"Deka, B., Dey, A., & Nirmala, S. R. (2018). Assamese connected digit recognition system. International Journal of Research in Signal Processing, Computing and Communication System Design, 4, 9\u201312.","journal-title":"International Journal of Research in Signal Processing, Computing and Communication System Design"},{"key":"9976_CR7","doi-asserted-by":"crossref","unstructured":"Deng, L., Li, J., Huang, J.-T., Yao, K., Yu, D., Seide, F., Seltzer, M., Zweig, G., He, X., Williams, J. et al. (2013). Recent advances in deep learning for speech research at Microsoft. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 8604\u20138608). IEEE.","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"9976_CR8","doi-asserted-by":"crossref","unstructured":"Dhanashri, D., & Dhonde, S. (2017). Isolated word speech recognition system using deep neural networks. In Proceedings of the international conference on data engineering and communication technology (pp. 9\u201317). Springer.","DOI":"10.1007\/978-981-10-1675-2_2"},{"key":"9976_CR9","volume-title":"Fundamentals of neural networks: architectures, algorithms and applications","author":"LV Fausett","year":"2006","unstructured":"Fausett, L. V. (2006). Fundamentals of neural networks: architectures, algorithms and applications. Pearson Education India."},{"key":"9976_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2298\/JAC1001001G","volume":"20","author":"W Gevaert","year":"2010","unstructured":"Gevaert, W., Tsenov, G., & Mladenov, V. (2010). Neural networks used for speech recognition. Journal of Automatic Control, 20, 1\u20137.","journal-title":"Journal of Automatic Control"},{"key":"9976_CR11","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1162\/COLI_r_00312","volume":"44","author":"Y Goldberg","year":"2018","unstructured":"Goldberg, Y., Hirst, G., Liu, Y., & Zhang, M. (2018). Neural Network Methods for Natural Language Processing. Computational Linguistics, 44, 193\u2013195.","journal-title":"Computational Linguistics"},{"key":"9976_CR12","first-page":"7","volume":"7","author":"A Gope","year":"2018","unstructured":"Gope, A. (2018). The phoneme inventory of Sylheti: Acoustic evidences. Journal of Advanced Linguistic Studies, 7, 7\u201337.","journal-title":"Journal of Advanced Linguistic Studies"},{"key":"9976_CR13","doi-asserted-by":"crossref","unstructured":"Hori, T., Hori, C., Watanabe, S., & Hershey, J. R. (2016). Minimum word error training of long short-term memory recurrent neural network language models for speech recognition. In 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5990\u20135994). IEEE.","DOI":"10.1109\/ICASSP.2016.7472827"},{"key":"9976_CR14","doi-asserted-by":"publisher","first-page":"319","DOI":"10.19113\/sdufbed.12798","volume":"22","author":"UA Kimanuka","year":"2018","unstructured":"Kimanuka, U. A., & B\u00fcy\u00fck, O. (2018). Turkish speech recognition based on deep neural networks. S\u00fcleyman Demirel \u00dcniversitesi Fen Bilimleri Enstit\u00fcs\u00fc Dergisi, 22, 319\u2013329.","journal-title":"S\u00fcleyman Demirel \u00dcniversitesi Fen Bilimleri Enstit\u00fcs\u00fc Dergisi"},{"key":"9976_CR15","doi-asserted-by":"publisher","unstructured":"Kunze, J., Kirsch, L., Kurenkov, I., Krug, A., Johannsmeier, J., & Stober,S. (2017). Transfer learning for speech recognition on a budget. In Proceedings of the 2nd workshop on representation learning for NLP (pp. 168\u2013177). Association for Computational Linguistics. https:\/\/www.aclweb.org\/anthology\/W17-2620. https:\/\/doi.org\/10.18653\/v1\/W17-2620.","DOI":"10.18653\/v1\/W17-2620"},{"key":"9976_CR16","doi-asserted-by":"publisher","first-page":"133","DOI":"10.14419\/ijet.v7i4.6.20449","volume":"7","author":"D Nagajyothi","year":"2018","unstructured":"Nagajyothi, D., & Siddaiah, P. (2018). Speech recognition using convolutional neural networks. International Journal of Engineering and Technology, 7, 133.","journal-title":"International Journal of Engineering and Technology"},{"key":"9976_CR17","doi-asserted-by":"publisher","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","volume":"7","author":"AB Nassif","year":"2019","unstructured":"Nassif, A. B., Shahin, I., Attili, I., Azzeh, M., & Shaalan, K. (2019). Speech recognition using deep neural networks: A systematic review. IEEE Access, 7, 19143\u201319165.","journal-title":"IEEE Access"},{"key":"9976_CR18","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1080\/02564602.2015.1010611","volume":"32","author":"J Padmanabhan","year":"2015","unstructured":"Padmanabhan, J., & Johnson Premkumar, M. J. (2015). Machine learning in automatic speech recognition: A survey. IETE Technical Review, 32, 240\u2013251.","journal-title":"IETE Technical Review"},{"issue":"1","key":"9976_CR19","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1515\/jisys-2018-0372","volume":"29","author":"V Passricha","year":"2020","unstructured":"Passricha, V., & Aggarwal, R. K. (2020). A hybrid of deep CNN and bidirectional LSTM for automatic speech recognition. Journal of Intelligent Systems, 29(1), 1261\u20131274.","journal-title":"Journal of Intelligent Systems"},{"key":"9976_CR20","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Povey, D., & Khudanpur, S. (2015). A time delay neural network architecture for efficient modelling of long temporal contexts. In Sixteenth annual conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2015-647"},{"key":"9976_CR21","volume-title":"Fundamentals of speech recognition","author":"L Rabiner","year":"1993","unstructured":"Rabiner, L., & Juang, B. H. (1993). Fundamentals of speech recognition. PTR Prentice-Hall. Inc."},{"key":"9976_CR22","doi-asserted-by":"crossref","unstructured":"Sharma, M., Sarma, M., & Sarma, K. K. (2013). Recurrent neural network based approach to recognize Assamese vowels using experimentally derived acoustic-phonetic features. In 2013 1st international conference on emerging trends and applications in computer science (pp. 140\u2013143).IEEE.","DOI":"10.1109\/ICETACS.2013.6691411"},{"key":"9976_CR23","doi-asserted-by":"crossref","unstructured":"Sharma, M., & Sarma, K. K. (2016). Learning aided mood and dialect recognition using telephonic speech. In 2016 International conference on accessibility to digital world (ICADW) (pp. 163\u2013167). IEEE.","DOI":"10.1109\/ICADW.2016.7942534"},{"key":"9976_CR24","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s40012-016-0145-5","volume":"5","author":"M Sharma","year":"2017","unstructured":"Sharma, M., & Sarma, K. K. (2017). Soft computation based spectral and temporal models of linguistically motivated Assamese telephonic conversation recognition. CSI Transactions on ICT, 5, 209\u2013216.","journal-title":"CSI Transactions on ICT"},{"key":"9976_CR25","unstructured":"Shrawankar, U., & Thakare, V. M. (2013). Techniques for feature extraction in speech recognition system: A comparative study. arXiv:1305.1145."},{"key":"9976_CR26","doi-asserted-by":"crossref","unstructured":"Sokolov, A., & Savchenko, A. V. (2019). Voice command recognition in intelligent systems using deep neural networks. In 2019 IEEE 17th world symposium on applied machine intelligence and informatics (SAMI) (pp.113\u2013116). IEEE.","DOI":"10.1109\/SAMI.2019.8782755"},{"key":"9976_CR27","doi-asserted-by":"crossref","unstructured":"Sumon, S. A., Chowdhury, J., Debnath, S., Mohammed, N., & Momen, S.(2018). Bangla short speech commands recognition using convolutional neural networks. In 2018 International conference on Bangla speech and language processing (ICBSLP), (pp. 1\u20136).","DOI":"10.1109\/ICBSLP.2018.8554395"},{"key":"9976_CR28","first-page":"533","volume":"1076","author":"M Telmem","year":"2020","unstructured":"Telmem, M., & Ghanou, Y. (2020). A comparative study of HMMs and CNN acoustic model in Amazigh recognition system. Advances in Intelligence Systems & Computing A, 1076, 533\u2013540.","journal-title":"Advances in Intelligence Systems & Computing A"},{"key":"9976_CR29","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/29.21701","volume":"37","author":"A Waibel","year":"1989","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. J. (1989). Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37, 328\u2013339.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9976_CR30","doi-asserted-by":"publisher","first-page":"644","DOI":"10.3390\/sym11050644","volume":"11","author":"D Wang","year":"2019","unstructured":"Wang, D., Wang, X., & Lv, S. (2019). End-to-end mandarin speech recognition combining CNN and BLSTM. Symmetry, 11, 644.","journal-title":"Symmetry"},{"key":"9976_CR31","doi-asserted-by":"crossref","unstructured":"Xie, Y., Le, L., Zhou, Y., & Raghavan, V. V. (2018). Deep learning for natural language processing. In Handbook of statistics (Vol. 38, pp. 317\u2013328). Elsevier.","DOI":"10.1016\/bs.host.2018.05.001"},{"key":"9976_CR32","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MCI.2018.2840738","volume":"13","author":"T Young","year":"2018","unstructured":"Young, T., Hazarika, D., Poria, S., & Cambria, E. (2018). Recent trends in deep learning based natural language processing. IEEE Computational Intelligence Magazine, 13, 55\u201375.","journal-title":"IEEE Computational Intelligence Magazine"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-09976-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-022-09976-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-09976-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T11:45:03Z","timestamp":1655811903000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-022-09976-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,25]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["9976"],"URL":"https:\/\/doi.org\/10.1007\/s10772-022-09976-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,25]]},"assertion":[{"value":"23 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}