{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T03:00:19Z","timestamp":1780974019471,"version":"3.54.1"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132087","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T10:14:58Z","timestamp":1773828898000},"page":"132087","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Machine learning-Based acoustic model development for low-Resource ahirani speech recognition using a self-Generated curated corpus"],"prefix":"10.1016","volume":"319","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5996-4123","authenticated-orcid":false,"given":"Hruturaj","family":"Nikam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6745-4363","authenticated-orcid":false,"given":"Suryakanth V","family":"Gangashetty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132087_bib0001","unstructured":"An investigation of hybrid architectures for low resource multilingual speech recognition system in indian context. (1451). https:\/\/www.aclanthology.org\/2021.icon-main.25.pdf."},{"key":"10.1016\/j.eswa.2026.132087_bib0002","unstructured":"Amadeus, M., Casta\u00f1eda, W. A. C., Lobato, W., Aquino, N., 2024. Phonetically rich corpus construction for a low-resourced language. arXiv (Cornell University)http:\/\/arxiv.org\/abs\/2402.05794."},{"key":"10.1016\/j.eswa.2026.132087_sbref0003","doi-asserted-by":"crossref","DOI":"10.1186\/s13636-025-00395-5","article-title":"Comparative performance analysis of end-to-end asr models on indo-aryan and dravidian languages within india\u2019s linguistic landscape","volume":"2025","author":"Jain","year":"2025","journal-title":"EURASIP Journal on Audio Speech and Music Processing"},{"key":"10.1016\/j.eswa.2026.132087_bib0004","unstructured":"Anantrasirichai, N., Zhang, F., Bull, D., 2025. Artificial intelligence in creative industries: Advances prior to 2025, arXiv (Cornell University). http:\/\/arxiv.org\/abs\/2501.02725."},{"key":"10.1016\/j.eswa.2026.132087_bib0005","series-title":"Multilingual techniques for low resource automatic speech recognition","author":"Chuangsuwanich","year":"2016"},{"key":"10.1016\/j.eswa.2026.132087_bib0006","unstructured":"Dai, W., Dai, C., Qu, S., Li, J., Das, S., 2016. Very deep convolutional neural networks for raw waveforms, arxiv (cornell university). https:\/\/arxiv.org\/abs\/1610.00087."},{"key":"10.1016\/j.eswa.2026.132087_bib0007","unstructured":"Safonova, A., Yudina, T. A., Nadimanov, E., Davenport, C., 2022. Automatic speech recognition of low-resource languages based on chukchi, arxiv (cornell university). https:\/\/arxiv.org\/abs\/2210.05726."},{"key":"10.1016\/j.eswa.2026.132087_bib0008","unstructured":"Chakraborty, T., Prasad, M., Breiner, T., Ritchie, S., van Esch, D., 2021. Mining large-scale low-resource pronunciation data from wikipedia, arxiv (cornell university). 10.48550\/arxiv.2101.11575."},{"key":"10.1016\/j.eswa.2026.132087_bib0009","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1017\/S1356186315000486","article-title":"Colonial anthropology and the decline of the raj: caste, religion and political change in india in the early twentieth century","volume":"26","author":"Fuller","year":"2015","journal-title":"Journal of the Royal Asiatic Society"},{"key":"10.1016\/j.eswa.2026.132087_bib0010","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1111\/1467-9655.12654","article-title":"Ethnographic inquiry in colonial india: herbert risley, william crooke, and the study of tribes and castes","volume":"23","author":"Fuller","year":"2017","journal-title":"Journal of the Royal Anthropological Institute"},{"key":"10.1016\/j.eswa.2026.132087_bib0011","doi-asserted-by":"crossref","unstructured":"Ragni, A., Knill, K., Rath, S. P., Gales, M., 2014. Data augmentation for low resource languages. 10.21437\/interspeech.2014-207.","DOI":"10.21437\/Interspeech.2014-207"},{"key":"10.1016\/j.eswa.2026.132087_bib0012","doi-asserted-by":"crossref","unstructured":"Farooq, M. U., Hain, T., 2023. Learning cross-lingual mappings for data augmentation to improve low-resource speech recognition, arxiv (cornell university). https:\/\/arxiv.org\/abs\/2306.08577.","DOI":"10.21437\/Interspeech.2023-1613"},{"key":"10.1016\/j.eswa.2026.132087_bib0013","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","article-title":"Acoustic modeling using deep belief networks","volume":"20","author":"Mohamed","year":"2011","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"10.1016\/j.eswa.2026.132087_bib0014","doi-asserted-by":"crossref","unstructured":"Poria, S., Huang, X., (2025). Bhaasha, bh\u0101\u1e61\u0101, zaban: a survey for low-resourced languages in south asia - current stage and challenges,. (pp. 1386\u20131406). 10.18653\/v1\/2025.findings-emnlp.73.","DOI":"10.18653\/v1\/2025.findings-emnlp.73"},{"key":"10.1016\/j.eswa.2026.132087_bib0015","doi-asserted-by":"crossref","first-page":"1176","DOI":"10.3844\/jcssp.2025.1176.1186","article-title":"Enhancing indian language speech recognition systems with language-independent phonetic script: an experimental exploration","volume":"21","author":"Stephan","year":"2025","journal-title":"Journal of Computer Science"},{"key":"10.1016\/j.eswa.2026.132087_bib0016","series-title":"Towards building asr systems for the next billion users","first-page":"10813","volume":"vol. 36","author":"Javed","year":"2022"},{"key":"10.1016\/j.eswa.2026.132087_sbref0017","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition","volume":"29","author":"Hinton","year":"2012","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.eswa.2026.132087_bib0018","doi-asserted-by":"crossref","DOI":"10.1186\/s13636-021-00225-4","article-title":"Text-to-speech system for low-resource language using cross-lingual transfer learning and data augmentation","volume":"2021","author":"Byambadorj","year":"2021","journal-title":"EURASIP Journal on Audio Speech and Music Processing"},{"key":"10.1016\/j.eswa.2026.132087_bib0019","unstructured":"Geng, M., Littell, P., Pine, A., undefined, M., Tessier, R. Kuhn, 2025. Supporting sencoten language documentation efforts with automatic speech recognition. 10.48550\/ARXIV.2507.10827."},{"key":"10.1016\/j.eswa.2026.132087_bib0020","doi-asserted-by":"crossref","unstructured":"Li, J., Wu, Y., Gaur, Y., Wang, C., Zhao, R., Liu, S., 2020. On the comparison of popular end-to-end models for large scale speech recognition, arxiv (cornell university). 10.48550\/arxiv.2005.14327.","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"10.1016\/j.eswa.2026.132087_bib0021","doi-asserted-by":"crossref","unstructured":"Ribeiro, M. S., Comini, G., Lorenzo-Trueba, J., 2023. Improving grapheme-to-phoneme conversion by learning pronunciations from speech recordings, arxiv (cornell university). 10.48550\/arxiv.2307.16643.","DOI":"10.21437\/Interspeech.2023-816"},{"key":"10.1016\/j.eswa.2026.132087_bib0022","unstructured":"Kamble, A., Tathe, A., Kumbharkar, S., Bhandare, A., Mitra, A., 2023. Custom data augmentation for low resource asr using bark and retrieval-based voice conversion, arxiv (cornell university). 10.48550\/arxiv.2311.14836."},{"key":"10.1016\/j.eswa.2026.132087_bib0023","unstructured":"Muhammad, S. H. I., Sani, B., Gete, D. K., Ahamed, B. Y., Ahmad, I. S., Abdulmumin, I., Yimam, S. M., Bello, M. Y., & Hassan, S. (2025). Automatic speech recognition for african low-resource languages: challenges and future directions,. 10.48550\/ARXIV.2505.11690."},{"key":"10.1016\/j.eswa.2026.132087_bib0024","unstructured":"Muthukumar, D. B., Wotherspoon, S., Jiang, Z., & Kumar, P. (2020). Speech synthesis as augmentation for low-resource ASR, arxiv (cornell university). 10.48550\/arxiv.2012.13004."},{"key":"10.1016\/j.eswa.2026.132087_bib0025","doi-asserted-by":"crossref","unstructured":"Zeyer, A., Doetsch, P., Voigtlaender, P., Schl\u00fcter, R., Ney, H., 2017. A comprehensive study of deep bidirectional lstm rnns for acoustic modeling in speech recognition. (pp. 2462\u20132466). 10.1109\/icassp.2017.7952599.","DOI":"10.1109\/ICASSP.2017.7952599"},{"key":"10.1016\/j.eswa.2026.132087_bib0026","series-title":"Data augmentation, feature combination, and multilingual neural networks to improve asr and kws performance for low-resource languages","author":"T\u00fcske","year":"2014"},{"key":"10.1016\/j.eswa.2026.132087_bib0027","doi-asserted-by":"crossref","unstructured":"Kumar, R., Singh, S., Ratan, S., Raj, M., Sinha, S., lahiri, bornini, Seshadri, V., Bali, K., Ojha, A. K., 2022. Annotated speech corpus for low resource indian languages: awadhi, bhojpuri, braj and magahi, arxiv (cornell university). 10.48550\/arxiv.2206.12931.","DOI":"10.21437\/S4SG.2022-1"},{"key":"10.1016\/j.eswa.2026.132087_bib0028","unstructured":"Okal, E. A., Wanzare, L., Muchemi, L., Wanjawa, B., Ombui, E., Indede, F., McOnyango, O., & Odoyo, B. (2022). Phonemic representation and transcription for speech to text applications for under-resourced indigenous african languages: the case of kiswahili, arxiv (cornell university). 10.48550\/arXiv.2210.16537."},{"key":"10.1016\/j.eswa.2026.132087_bib0029","first-page":"476","article-title":"Fast offline transformer-based end-to-end automatic speech recognition for real-world applications","volume":"44","author":"Park","year":"2021","journal-title":"ETRI Journal"},{"key":"10.1016\/j.eswa.2026.132087_bib0030","unstructured":"Patil, A. (2014). Automatic speech recognition for ahirani language using hidden markov model toolkit (HTK)."},{"key":"10.1016\/j.eswa.2026.132087_bib0031","unstructured":"Rahman, M. S. I. R., Akter, S., & Aminur, M. (2025). Adaptability of ASR models on low-resource language: a comparative study of whisper and wav2vec-BERT on bangla,. 10.48550\/ARXIV.2507.01931."},{"key":"10.1016\/j.eswa.2026.132087_bib0032","article-title":"Deep learning for indian language processing: a focus on speech recognition systems","volume":"8","author":"Ranjan","year":"2021","journal-title":"Universal Research Reports"},{"key":"10.1016\/j.eswa.2026.132087_bib0033","doi-asserted-by":"crossref","first-page":"5873","DOI":"10.1109\/TAI.2024.3444742","article-title":"Recent advances in generative ai and large language models: current status, challenges, and perspectives","volume":"5","author":"Hagos","year":"2024","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132087_bib0034","unstructured":"Roux, T. H., Moritz, N., Hori, C., & Le, J. (2021). Advanced long-context end-to-end speech recognition using context-expanded transformers, arxiv (cornell university). 10.48550\/arxiv.2104.09426."},{"key":"10.1016\/j.eswa.2026.132087_bib0035","doi-asserted-by":"crossref","unstructured":"Alum\u00e4e, T., Kong, J., R\u00f5bnikov, D., 2023. Dialect adaptation and data augmentation for low-resource asr: taltech systems for the madasr 2023 challenge. (pp. 1\u20137). (vol. 33). 10.1109\/asru57964.2023.10389668.","DOI":"10.1109\/ASRU57964.2023.10389668"},{"key":"10.1016\/j.eswa.2026.132087_bib0036","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.specom.2013.07.008","article-title":"Automatic speech recognition for under-resourced languages: a survey","volume":"56","author":"Besacier","year":"2013","journal-title":"Speech Communication"},{"key":"10.1016\/j.eswa.2026.132087_bib0037","unstructured":"Linke, J., Wepner, S., Kubin, G., Schuppler, B., 2023. Using kaldi for automatic speech recognition of conversational austrian german, arxiv (cornell university). 10.48550\/arxiv.2301.06475."},{"key":"10.1016\/j.eswa.2026.132087_bib0038","article-title":"Google crowdsourced speech corpora and related open-source resources for low-resource languages and dialects: an overview, arxiv","author":"Butryna","year":"2020","journal-title":"(Cornell University)"},{"key":"10.1016\/j.eswa.2026.132087_bib0039","unstructured":"Matarazzo, A., Torlone, R., 2025. A survey on large language models with some insights on their capabilities and limitations. 10.48550\/ARXIV.2501.04040."},{"key":"10.1016\/j.eswa.2026.132087_bib0040","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N. K., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsk\u00fd, J., Stemmer, G., Vesel\u00fd, K., 2011. The kaldi speech recognition toolkit. http:\/\/publications.idiap.ch\/index.php\/publications\/showcite\/Povey_Idiap-RR-04-2012."},{"key":"10.1016\/j.eswa.2026.132087_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124119","article-title":"End-to-end automated speech recognition using a character based small scale transformer architecture","volume":"252","author":"Loubser","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132087_bib0042","first-page":"1384","article-title":"Languageuniversal phonetic representation in multilingual speech pretraining for low-resource speech recognition","author":"Feng","year":"2023","journal-title":"Interspeech 2022"},{"key":"10.1016\/j.eswa.2026.132087_bib0043","doi-asserted-by":"crossref","first-page":"163829","DOI":"10.1109\/ACCESS.2020.3020421","article-title":"Acoustic modeling based on deep learning for low-resource speech recognition: an overview","volume":"8","author":"Yu","year":"2020","journal-title":"IEEE Access"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426010006?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426010006?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T02:49:39Z","timestamp":1780973379000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426010006"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":43,"alternative-id":["S0957417426010006"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132087","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Machine learning-Based acoustic model development for low-Resource ahirani speech recognition using a self-Generated curated corpus","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132087","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132087"}}