{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:36:08Z","timestamp":1767339368939,"version":"3.28.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T00:00:00Z","timestamp":1707782400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T00:00:00Z","timestamp":1707782400000},"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\/s10772-024-10082-z","type":"journal-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T18:02:02Z","timestamp":1707847322000},"page":"87-99","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An amalgamation of integrated features with DeepSpeech2 architecture and improved spell corrector for improving Gujarati language ASR system"],"prefix":"10.1007","volume":"27","author":[{"given":"Mohit","family":"Dua","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhavesh","family":"Bhagat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shelza","family":"Dua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,13]]},"reference":[{"key":"10082_CR1","unstructured":"Amodei, D. et al. (2016). Deep Speech 2\u202f: End-to-end speech recognition in English and Mandarin. In Proceedings of the 33rd international conference on machine learning, 2016, (vol. 48, pp. 173\u2013182). Retrieved from https:\/\/proceedings.mlr.press\/v48\/amodei16.html"},{"key":"10082_CR2","doi-asserted-by":"crossref","unstructured":"Anoop, C. S., & Ramakrishnan, A. G. (2021, July). CTC-based end-to-end ASR for the low resource Sanskrit language with spectrogram augmentation. In 2021 National conference on communications (NCC) (pp. 1\u20136). IEEE.","DOI":"10.1109\/NCC52529.2021.9530162"},{"key":"10082_CR3","doi-asserted-by":"crossref","unstructured":"Bhogale, K., Raman, A., Javed, T., Doddapaneni, S., Kunchukuttan, A., Kumar, P., & Khapra, M. M. (2023, June). Effectiveness of mining audio and text pairs from public data for improving ASR systems for low-resource languages. In ICASSP 2023\u20132023 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ICASSP49357.2023.10096933"},{"key":"10082_CR4","doi-asserted-by":"crossref","unstructured":"Billa, J. (2018). ISI ASR system for the low resource speech recognition challenge for Indian languages. In INTERSPEECH, 2018.","DOI":"10.21437\/Interspeech.2018-2473"},{"key":"10082_CR5","doi-asserted-by":"publisher","unstructured":"Cho, K., et al. (2014). Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), Oct 2014, pp. 1724\u20131734. https:\/\/doi.org\/10.3115\/v1\/D14-1179.","DOI":"10.3115\/v1\/D14-1179"},{"key":"10082_CR6","doi-asserted-by":"publisher","first-page":"6442","DOI":"10.15680\/ijircce.2015.0307012","volume":"03","author":"D Dave","year":"2015","unstructured":"Dave, D. (2015). An approach to increase word recognition accuracy in Gujarati language. International Journal of Innovative Research in Computer and Communication Engineering, 3, 6442\u20136450. https:\/\/doi.org\/10.15680\/ijircce.2015.0307012","journal-title":"Int. J. Innov. Res. Comput. Commun. Eng."},{"issue":"8","key":"10082_CR7","doi-asserted-by":"publisher","first-page":"958","DOI":"10.24018\/ejeng.2020.5.8.2077","volume":"5","author":"AM Deshmukh","year":"2020","unstructured":"Deshmukh, A. M. (2020). Comparison of hidden Markov model and recurrent neural network in automatic speech recognition. European Journal of Engineering and Technology Research, 5(8), 958\u2013965. https:\/\/doi.org\/10.24018\/ejeng.2020.5.8.2077","journal-title":"Eur. J. Eng. Technol. Res."},{"issue":"1","key":"10082_CR8","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1515\/jisys-2017-0618","volume":"29","author":"M Dua","year":"2018","unstructured":"Dua, M., Aggarwal, R. K., & Biswas, M. (2018). Discriminative training using noise robust integrated features and refined HMM modeling. Journal of Intelligent Systems, 29(1), 327\u2013344.","journal-title":"Journal of Intelligent Systems"},{"key":"10082_CR9","doi-asserted-by":"publisher","first-page":"2301","DOI":"10.1007\/s12652-018-0828-x","volume":"10","author":"M Dua","year":"2019","unstructured":"Dua, M., Aggarwal, R. K., & Biswas, M. (2019). GFCC based discriminatively trained noise robust continuous ASR system for Hindi language. Journal of Ambient Intelligence and Humanized Computing, 10, 2301\u20132314.","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"key":"10082_CR10","unstructured":"Dubey, P., & Shah, B. (2022). Deep speech based end-to-end automated speech recognition (ASR) for Indian-English accents. arXiv preprint arXiv:2204.00977."},{"key":"10082_CR11","unstructured":"Forsberg, M. (2003). Why is speech recognition difficult."},{"key":"10082_CR12","doi-asserted-by":"crossref","unstructured":"Gaudani, H., & Patel, N. M. (2022). Comparative study of robust feature extraction techniques for ASR for limited resource Hindi language. In Proceedings of second international conference on sustainable expert systems: ICSES 2021 (pp. 763\u2013775). Springer Nature.","DOI":"10.1007\/978-981-16-7657-4_62"},{"key":"10082_CR13","unstructured":"Graves, A., & Jaitly, N. (2014). Towards end-to-end speech recognition with recurrent neural networks. In Proceedings of the 31st international conference on machine learning, 2014, (vol. 32, no. 2, pp. 1764\u20131772). Retrieved from https:\/\/proceedings.mlr.press\/v32\/graves14.html"},{"key":"10082_CR14","doi-asserted-by":"crossref","unstructured":"Graves, A., et al. (2006). Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. In Proceedings of the 23rd international conference on machine learning, 2006.","DOI":"10.1145\/1143844.1143891"},{"key":"10082_CR15","doi-asserted-by":"crossref","unstructured":"Hu, Y., Jing, X., Ko, Y. L., & Rayz, J. (2021). Misspelling correction with pre-trained contextual language model.","DOI":"10.1109\/ICCICC50026.2020.9450253"},{"key":"10082_CR16","doi-asserted-by":"crossref","unstructured":"Joshi, B., Bhatta, B., Panday, S. P., & Maharjan, R. K. (2022). A novel deep learning based nepali speech recognition. In Innovations in electrical and electronic engineering: Proceedings of ICEEE 2022, (Vol. 2, pp. 433\u2013443). Springer.","DOI":"10.1007\/978-981-19-1677-9_39"},{"key":"10082_CR17","doi-asserted-by":"publisher","unstructured":"Krishna, H., Gurugubelli, K., Vegesna, V., & Vuppala, A. (2018). An exploration towards joint acoustic modeling for Indian languages: IIIT-h submission for low resource speech recognition challenge for Indian languages, INTERSPEECH 2018 (pp. 3192\u20133196). https:\/\/doi.org\/10.21437\/Interspeech.2018-1584.","DOI":"10.21437\/Interspeech.2018-1584"},{"key":"10082_CR18","unstructured":"Lakshminarayanan, V. (2022). Impact of noise in automatic speech recognition for low-resourced languages, Doctoral dissertation, Rochester Institute of Technology."},{"key":"10082_CR19","doi-asserted-by":"crossref","unstructured":"Maji, B., Swain, M., & Panda, R. (2022). A feature selection based parallelized CNN-BiGRU network for speech emotion recognition in Odia language.","DOI":"10.21203\/rs.3.rs-1529387\/v1"},{"key":"10082_CR20","doi-asserted-by":"publisher","unstructured":"Patel, D., & Goswami, M. (2014). Word level correction in Gujarati document using probabilistic approach. https:\/\/doi.org\/10.1109\/ICGCCEE.2014.6921395.","DOI":"10.1109\/ICGCCEE.2014.6921395"},{"key":"10082_CR21","doi-asserted-by":"publisher","DOI":"10.1145\/3483446","author":"D Raval","year":"2021","unstructured":"Raval, D., Pathak, V., Patel, M., & Bhatt, B. (2021). Improving deep learning based automatic speech recognition for Gujarati. ACM Transactions on Asian and Low-Resource Language and Information Processing. https:\/\/doi.org\/10.1145\/3483446","journal-title":"ACM Transactions on Asian and Low-Resource Language and Information Processing"},{"key":"10082_CR22","unstructured":"Scharenborg, O., Ciannella, F., Palaskar, S., Black, A., Metze, F., Ondel, L., & Hasegawa-Johnson, M. (2017). Building an ASR system for a low-resource language through the adaptation of a high-resource language ASR system: Preliminary results. In Proceedings of international conference on natural language, signal and speech processing (ICNLSSP)\u00a0(pp. 26\u201330)."},{"issue":"11","key":"10082_CR23","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673\u20132681. https:\/\/doi.org\/10.1109\/78.650093","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10082_CR24","unstructured":"Srivastava, B., Abraham, B., Sitaram, S., Mehta, R., & Jyothi, P. (2019). End-to-end ASR for code-switched Hindi-English speech."},{"key":"10082_CR25","unstructured":"Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. In Advances in neural information processing systems, 2014 (Vol. 27). https:\/\/proceedings.neurips.cc\/paper\/2014\/file\/a14ac55a4f27472c5d894ec1c3c743d2Paper.pdf"},{"key":"10082_CR26","doi-asserted-by":"crossref","unstructured":"Tailor, J. H., & Shah, D. B. (2018). HMM-based lightweight speech recognition system for Gujarati language.","DOI":"10.1007\/978-981-10-3920-1_46"},{"key":"10082_CR27","doi-asserted-by":"crossref","unstructured":"Toshniwal, S., et al. (2017). Multilingual speech recognition with a single end-to-end model.","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"10082_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, S., Huang, H., Liu, J., & Li, H. (2020). Spelling error correction with soft-masked BERT.","DOI":"10.18653\/v1\/2020.acl-main.82"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10082-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-024-10082-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10082-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T06:16:56Z","timestamp":1731305816000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-024-10082-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,13]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["10082"],"URL":"https:\/\/doi.org\/10.1007\/s10772-024-10082-z","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2024,2,13]]},"assertion":[{"value":"9 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 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":"I, Mohit Dua, on the behalf of all the authors declare that: this study did not receive any finding from any resource, all the authors and the submitted manuscript do not have any conflict of interest and this article does not contain any studies with human participants or animal performed by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}