{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:50:10Z","timestamp":1761130210639,"version":"3.44.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T00:00:00Z","timestamp":1744588800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T00:00:00Z","timestamp":1744588800000},"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":[[2025,6]]},"DOI":"10.1007\/s10772-025-10180-6","type":"journal-article","created":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T09:47:06Z","timestamp":1744624026000},"page":"369-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards development of the first continuous speech recognition system in Indian language Nagpuri"],"prefix":"10.1007","volume":"28","author":[{"given":"Shubhojeet","family":"Paul","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vandana","family":"Bhattacharjee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sujan Kumar","family":"Saha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,14]]},"reference":[{"key":"10180_CR1","doi-asserted-by":"crossref","unstructured":"Al Amin, M. A., Islam, M. T., Kibria, S., & Rahman, M. S. (2019). Continuous Bengali speech recognition based on deep neural network. In International conference on electrical, computer and communication engineering (ECCE), (pp. 1\u20136). IEEE.","DOI":"10.1109\/ECACE.2019.8679341"},{"key":"10180_CR2","first-page":"12449","volume":"33","author":"A. Baevski","year":"2020","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., & Auli, M. (2020). wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems, 33, 12449\u201312460.","journal-title":"Adv Neural Inf Process Syst"},{"key":"10180_CR3","doi-asserted-by":"publisher","unstructured":"Chowdary, D. E., Ganesan, R., Dabbara, H., Jyothish Lal, G., & Premjith, B. (2024). Transformer-based multilingual automatic speech recognition (ASR) model for dravidian languages. In L. A. Kumar, D. K. Renuka, B. R. Chakravarthi & T. Mandl (Eds), Automatic speech recognition and translation for low-resource languages, (pp. 259\u2013273). https:\/\/doi.org\/10.1002\/9781394214624.ch13","DOI":"10.1002\/9781394214624.ch13"},{"key":"10180_CR4","doi-asserted-by":"crossref","unstructured":"Deepa, R., Jayalakshmi, V., Thilakavathy, P., Manikandan, G., & Suren- Dran, R. (2024). Custom transformer-based approach for enhanced Bengali automatic speech recognition. In 2024 First international conference on innovations in communications, electrical and computer engineering (ICICEC), (pp. 1\u20138). IEEE.","DOI":"10.1109\/ICICEC62498.2024.10808418"},{"key":"10180_CR5","doi-asserted-by":"crossref","unstructured":"Dey, A., Lalhminghlui, W., Sarmah, P., Samudravijaya, K., Mahadeva Prasarma, S. R., Sinha, R., & Nirmala, S. R. (2017). Mizo phone recognition system. In 2017 14th IEEE India council international conference (INDICON), (pp. 1\u20135). IEEE.","DOI":"10.1109\/INDICON.2017.8487726"},{"key":"10180_CR6","doi-asserted-by":"crossref","unstructured":"Dhanjal, S., & Bhatia, S. S. (2013). Development of a standard text and speech corpus for the Punjabi language. In 2013 International conference oriental COCOSDA and 2013 conference on Asian spoken language research and evaluation, (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICSDA.2013.6709891"},{"key":"10180_CR7","doi-asserted-by":"crossref","unstructured":"Diwan, A., Vaideeswaran, R., Shah, S., Singh, A., Raghavan, S., Khare, S., Unni, V., Vyas, S., Rajpuria, A., Yarra, C., Mittal, R. A., Ghosh, P., Jyothi, P., Bali, K., Seshadri, V., Sitaram, S., Bharadwaj, S., Nanavati, J., Nanavati, R.,\u2026 Abraham, B. (2021) Multilingual and code-switching ASR challenges for low resource Indian languages. arXiv preprint arXiv:2104.00235","DOI":"10.21437\/Interspeech.2021-1339"},{"key":"10180_CR8","doi-asserted-by":"crossref","unstructured":"Dua, M., Aggarwal, R. K., Kadyan, V., & Dua, S. (2012a). Punjabi speech to text system for connected words. In Fourth international conference on advances in recent technologies in communication and computing, (pp. 206\u2013209). IET.","DOI":"10.1049\/cp.2012.2528"},{"issue":"4","key":"10180_CR9","first-page":"359","volume":"9","author":"M. Dua","year":"2012","unstructured":"Dua, M., Aggarwal, R. K., Kadyan, V., & Dua, S. (2012b). Punjabi automatic speech recognition using HTK. International Journal of Computer Science Issues, 9(4), 359.","journal-title":"Int J Comput Sci Iss (IJCSI)"},{"key":"10180_CR10","unstructured":"Dupre, G., Nefdt, R., & Stanton, K. (2023). What phonology is and why it should be. In Gabe Dupre, Ryan Nefdt & Kate Stanton (Eds), The Oxford handbook on the philosophy of linguistics. https:\/\/lingbuzz.net\/lingbuzz\/007518\/v1.pdf"},{"key":"10180_CR11","volume-title":"Ethnologue: Lan- guages of the World","author":"M. Eberhard David","year":"2022","unstructured":"Eberhard David, M., Gary, F. S., & Charles, D. F. (2022). Ethnologue: Lan- guages of the World. In Twenty-fifth SIL International. https:\/\/www.ethnologue.com\/guides\/countries-most-languages","edition":"Twenty-fifth"},{"issue":"01","key":"10180_CR12","first-page":"21","volume":"1","author":"B. W. Gawali","year":"2011","unstructured":"Gawali, B. W., Gaikwad, S., Yannawar, P., & Mehrotra, S. C. (2011). Marathi isolated word recognition system using MFCC and DTW features. ACEEE International Journal on Information Technology, 1(01), 21\u201324.","journal-title":"ACEEE Int J Inf Technol"},{"issue":"1","key":"10180_CR13","first-page":"379","volume":"2","author":"W. Ghai","year":"2012","unstructured":"Ghai, W., & Singh, N. (2012). Analysis of automatic speech recognition systems for Indo-Aryan languages: Punjabi a case study. International Journal of Soft Computing and Engineering, 2(1), 379\u2013385.","journal-title":"Int J Soft Comput Eng (IJSCE)"},{"key":"10180_CR14","doi-asserted-by":"crossref","unstructured":"Ghai, W., & Singh, N. (2013). Continuous speech recognition for Punjabi language. International Journal of Computer Applications, 72(14).","DOI":"10.5120\/12563-9002"},{"key":"10180_CR15","doi-asserted-by":"crossref","unstructured":"Gulati, A., Qin, J., Chiu, C. C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., & Pang, R. (2020). Conformer: Convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100. https:\/\/arxiv.org\/abs\/2005.08100","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"10180_CR16","unstructured":"International Phonetic Association. The IPA chart. [Online] Available: https:\/\/www.internationalphoneticassociation.org\/content\/ipa-chart (Accessed July 4, 2024)"},{"key":"10180_CR17","doi-asserted-by":"crossref","unstructured":"Karan, B., Sahoo, J., & Sahu, P. K. (2015). Automatic speech recognition based Odia System. In 2015 International conference on microwave, optical and communication engineering (ICMOCE), (pp. 353\u2013356). IEEE.","DOI":"10.1109\/ICMOCE.2015.7489765"},{"key":"10180_CR18","doi-asserted-by":"crossref","unstructured":"Kaur, A., & Singh, A. (2016). Power-normalized cepstral coefficients (PNCC) for Punjabi automatic speech recognition using phone based modelling in HTK. In 2016 2nd international conference on applied and theoretical computing and communication technology (iCATccT), (pp. 372\u2013375). IEEE.","DOI":"10.1109\/ICATCCT.2016.7912026"},{"key":"10180_CR20","unstructured":"Krishna, D. N. (2021). A dual-decoder conformer for multilingual speech recognition. arXiv:2109.03277v1. arXiv. https:\/\/arxiv.org\/abs\/2109.03277v1"},{"key":"10180_CR21","doi-asserted-by":"crossref","unstructured":"Kumar, A., Dua, M., & Choudhary, T. (2014). Continuous Hindi speech recognition using Gaussian mixture HMM. In 2014 IEEE students\u2019 conference on electrical, electronics and computer science, (pp. 1\u20135). IEEE.","DOI":"10.1109\/SCEECS.2014.6804519"},{"key":"10180_CR22","unstructured":"Kumar, K., & Agarwal, R. K. (2011). Hindi speech recognition system using HTK. International Journal of Computing and Business Research 2(2), ISSN (Online):2229\u20136166."},{"key":"10180_CR23","volume-title":"The IIT Bombay English-Hindi Parallel Corpus, European Language Resources Association (ELRA)","author":"A. Kunchukuttan","year":"2018","unstructured":"Kunchukuttan, A., Mehta, P., & Bhattacharyya, P. (2018). The IIT Bombay English-Hindi parallel corpus. In Proceedings of the eleventh international conference on language resources and evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA)."},{"key":"10180_CR24","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1007\/s12046-013-0160-2","volume":"38","author":"C. Kurian","year":"2013","unstructured":"Kurian, C., & Balakrishnan, K. (2013). Connected digit speech recognition system for Malayalam language. Sadhana, 38, 1339\u20131346.","journal-title":"Sadhana"},{"key":"10180_CR25","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/s10772-024-10132-6","volume":"27","author":"M. K. Majhi","year":"2024","unstructured":"Majhi, M. K., & Saha, S. K. (2024). An automatic speech recognition system in Odia language using attention mechanism and data augmentation. International Journal of Speech Technology, 27, 717\u2013728.","journal-title":"Int J Speech Technol"},{"key":"10180_CR26","unstructured":"Mirishkar, G., Yadavalli, A., & Vuppala, A. K. (2021). An investigation of hybrid archtectures for low resource multilingual speech recognition system in Indian context. In Proceedings of ICON 2021, (pp. 205\u2013212). NLP Association of India."},{"key":"10180_CR27","doi-asserted-by":"crossref","unstructured":"Moncy, A. M., Athira, M., Jasmin, H., & Rajan, R. (2020). Automatic speech recognition in Malayalam using DNN-based acoustic modelling. In 2020 IEEE recent advances in intelligent computational systems (RAICS), (pp. 170\u2013174). IEEE.","DOI":"10.1109\/RAICS51191.2020.9332493"},{"key":"10180_CR28","doi-asserted-by":"crossref","unstructured":"Pham, N. Q., Nguyen, T. S., Niehues, J., M\u00fcller, M., St\u00fcker, S., & Waibel, A. (2019). Very deep self-attention networks for end-to-end speech recognition. arXiv:1904.13377. ArXiv. https:\/\/arxiv.org\/abs\/1904.13377","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"10180_CR29","unstructured":"Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2023). Robust speech recognition via large-scale weak supervision. In International conference on machine learning (pp. 28492\u201328518). PMLR."},{"key":"10180_CR30","doi-asserted-by":"crossref","unstructured":"Samudravijaya, K. (2021). Indian language speech label (ILSL): A de facto national Standard. In Advances in speech and music technology: Proceedings of FRSM 2020, (pp. 449\u2013460). Springer.","DOI":"10.1007\/978-981-33-6881-1_36"},{"key":"10180_CR31","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., & Auli, M. (2019). wav2vec: Unsupervised pre-training for speech recognition. arXiv preprint arXiv:1904.05862.","DOI":"10.21437\/Interspeech.2019-1873"},{"issue":"5","key":"10180_CR32","doi-asserted-by":"publisher","first-page":"3673","DOI":"10.1007\/s10462-019-09775-8","volume":"53","author":"A. Singh","year":"2020","unstructured":"Singh, A., Kadyan, V., Kumar, M., & Bassan, N. (2020). ASRoIL: A comprehensive survey for automatic speech recognition of Indian languages. Artificial Intelligence Review, 53(5), 3673\u20133704.","journal-title":"Artif Intell Rev"},{"key":"10180_CR33","first-page":"100","volume":"8","author":"A. Thakur","year":"2011","unstructured":"Thakur, A., Singla, N., & Patil, V. V. (2011). Design of Hindi key word recognition system for home automation system using MFCC and DTW. International Journal of Advanced Engineering Sciences and Technologies, 8, 100\u2013106.","journal-title":"Int J Adv Eng Sci Technol"},{"key":"10180_CR34","doi-asserted-by":"crossref","unstructured":"Upadhyaya, P., Farooq, O., Abidi, M. R., & Varshney, Y. V. (2017). Continuous Hindi speech recognition model based on Kaldi ASR toolkit. In International conference on wireless communications, signal processing and networking (WiSPNET), (pp. 786\u2013789). IEEE.","DOI":"10.1109\/WiSPNET.2017.8299868"},{"key":"10180_CR35","doi-asserted-by":"crossref","unstructured":"Upadhyaya, P., Mittal, S. K., Farooq, O., Varshney, Y. V., & Abidi, M. R. (2019). Continuous Hindi speech recognition using Kaldi ASR based on deep neural network. Machine Intelligence and Signal Analysis, 303\u2013311.","DOI":"10.1007\/978-981-13-0923-6_26"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-025-10180-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-025-10180-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-025-10180-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T11:06:00Z","timestamp":1757156760000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-025-10180-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,14]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10180"],"URL":"https:\/\/doi.org\/10.1007\/s10772-025-10180-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2025,4,14]]},"assertion":[{"value":"13 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2025","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}