{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T15:54:08Z","timestamp":1776268448114,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T00:00:00Z","timestamp":1704326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Mphasis F1 Foundation"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,4]]},"DOI":"10.1145\/3632410.3632483","type":"proceedings-article","created":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T18:15:16Z","timestamp":1704305716000},"page":"553-557","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Knowledge Management Framework Over Low Resource Indian Colloquial Language Audio Contents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9404-8250","authenticated-orcid":false,"given":"Sharath","family":"Srivatsa","sequence":"first","affiliation":[{"name":"International Institute of Information Technology, Bangalore, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2264-2642","authenticated-orcid":false,"given":"Aparna","family":"M","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology, Bangalore, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9180-0422","authenticated-orcid":false,"given":"Sai Madhavan","family":"G","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology, Bangalore, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9588-6550","authenticated-orcid":false,"given":"Srinath","family":"Srinivasa","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology, Bangalore, India"}]}],"member":"320","published-online":{"date-parts":[[2024,1,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","unstructured":"Madhavaraj A Bharathi Pilar and Ramakrishnan\u00a0A G. 2022. Knowledge-driven Subword Grammar Modeling for Automatic Speech Recognition in Tamil and Kannada. https:\/\/doi.org\/10.48550\/ARXIV.2207.13333","DOI":"10.48550\/ARXIV.2207.13333"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","unstructured":"Madhavaraj A Bharathi Pilar and Ramakrishnan\u00a0A G. 2022. Subword Dictionary Learning and Segmentation Techniques for Automatic Speech Recognition in Tamil and Kannada. https:\/\/doi.org\/10.48550\/ARXIV.2207.13331","DOI":"10.48550\/ARXIV.2207.13331"},{"key":"e_1_3_2_2_3_1","volume-title":"Advances in Neural Information Processing Systems, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.). Vol.\u00a034. Curran Associates","author":"Baevski Alexei","year":"2021","unstructured":"Alexei Baevski, Wei-Ning Hsu, Alexis CONNEAU, and Michael Auli. 2021. Unsupervised Speech Recognition. In Advances in Neural Information Processing Systems, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.). Vol.\u00a034. Curran Associates, Inc., 27826\u201327839. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/ea159dc9788ffac311592613b7f71fbb-Paper.pdf"},{"key":"e_1_3_2_2_4_1","volume-title":"Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates, Inc., 12449\u201312460. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/92d1e1eb1cd6f9fba3227870bb6d7f07-Paper.pdf"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.kmrp.8500090"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","unstructured":"William Chan Daniel Park Chris Lee Yu Zhang Quoc Le and Mohammad Norouzi. 2021. SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network. arxiv:2104.02133\u00a0[cs.CL] https:\/\/doi.org\/10.48550\/arXiv.2104.02133","DOI":"10.48550\/arXiv.2104.02133"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","unstructured":"Guoguo Chen Shuzhou Chai Guanbo Wang Jiayu Du Wei-Qiang Zhang Chao Weng Dan Su Daniel Povey Jan Trmal Junbo Zhang Mingjie Jin Sanjeev Khudanpur Shinji Watanabe Shuaijiang Zhao Wei Zou Xiangang Li Xuchen Yao Yongqing Wang Yujun Wang Zhao You and Zhiyong Yan. 2021. GigaSpeech: An Evolving Multi-domain ASR Corpus with 10 000 Hours of Transcribed Audio. arxiv:2106.06909\u00a0[cs.SD] https:\/\/doi.org\/10.48550\/arXiv.2106.06909","DOI":"10.48550\/arXiv.2106.06909"},{"key":"e_1_3_2_2_8_1","volume-title":"Fourth International workshop on spoken language technologies for under-resourced languages (SLTU-2014)","author":"Gales JF","year":"2014","unstructured":"Mark\u00a0JF Gales, Kate\u00a0M Knill, Anton Ragni, and Shakti\u00a0P Rath. 2014. Speech recognition and keyword spotting for low-resource languages: Babel project research at cued. In Fourth International workshop on spoken language technologies for under-resourced languages (SLTU-2014). International Speech Communication Association (ISCA), 16\u201323."},{"key":"e_1_3_2_2_9_1","unstructured":"Daniel Galvez Greg Diamos Juan Torres Keith Achorn Juan Cer\u00f3n Anjali Gopi David Kanter Max Lam Mark Mazumder and Vijay Janapa\u00a0Reddi. 2021. The People\u2019s Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks J.\u00a0Vanschoren and S.\u00a0Yeung (Eds.). Vol.\u00a01. Curran. https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/202cb962ac59075b964b07152d234b70-Paper-round1.pdf"},{"key":"e_1_3_2_2_10_1","unstructured":"M. Harper. [n. d.]. IARPA Babel Program. http:\/\/www.iarpa.gov\/Programs\/ia\/Babel\/babel.html."},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference (LREC). European Language Resources Association (ELRA)","author":"He Fei","year":"2020","unstructured":"Fei He, Shan-Hui\u00a0Cathy Chu, Oddur Kjartansson, Clara Rivera, Anna Katanova, Alexander Gutkin, Isin Demirsahin, Cibu Johny, Martin Jansche, Supheakmungkol Sarin, and Knot Pipatsrisawat. 2020. Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems. In Proceedings of The 12th Language Resources and Evaluation Conference (LREC). European Language Resources Association (ELRA), Marseille, France, 6494\u20136503. https:\/\/www.aclweb.org\/anthology\/2020.lrec-1.800"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707770"},{"key":"e_1_3_2_2_13_1","volume-title":"Soviet physics doklady, Vol.\u00a010","author":"I Levenshtein","unstructured":"Vladimir\u00a0I Levenshtein 1966. Binary codes capable of correcting deletions, insertions, and reversals. In Soviet physics doklady, Vol.\u00a010. Soviet Union, 707\u2013710."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2212.10168"},{"key":"e_1_3_2_2_15_1","volume-title":"Scaling Speech Technology to 1,000+ Languages. arXiv","author":"Pratap Vineel","year":"2023","unstructured":"Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, Zhaoheng Ni, Apoorv Vyas, Maryam Fazel-Zarandi, Alexei Baevski, Yossi Adi, Xiaohui Zhang, Wei-Ning Hsu, Alexis Conneau, and Michael Auli. 2023. Scaling Speech Technology to 1,000+ Languages. arXiv (2023)."},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0202)","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Tao Xu, Greg Brockman, Christine Mcleavey, and Ilya Sutskever. 2023. Robust Speech Recognition via Large-Scale Weak Supervision. In Proceedings of the 40th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 28492\u201328518. https:\/\/proceedings.mlr.press\/v202\/radford23a.html"},{"key":"e_1_3_2_2_17_1","volume-title":"End-to-end speech recognition and keyword search on low-resource languages. In 2017 ieee international conference on acoustics, speech and signal processing (icassp)","author":"Rosenberg Andrew","unstructured":"Andrew Rosenberg, Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, and Michael Picheny. 2017. End-to-end speech recognition and keyword search on low-resource languages. In 2017 ieee international conference on acoustics, speech and signal processing (icassp). IEEE, 5280\u20135284."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","unstructured":"Salah Zaiem Robin Algayres Titouan Parcollet Slim Essid and Mirco Ravanelli. 2023. Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study. arxiv:2303.06740\u00a0[eess.AS] https:\/\/doi.org\/10.48550\/arXiv.2303.06740","DOI":"10.48550\/arXiv.2303.06740"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"}],"event":{"name":"CODS-COMAD 2024: 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","location":"Bangalore India","acronym":"CODS-COMAD 2024"},"container-title":["Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3632410.3632483","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3632410.3632483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:34:38Z","timestamp":1755869678000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3632410.3632483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,4]]},"references-count":19,"alternative-id":["10.1145\/3632410.3632483","10.1145\/3632410"],"URL":"https:\/\/doi.org\/10.1145\/3632410.3632483","relation":{},"subject":[],"published":{"date-parts":[[2024,1,4]]},"assertion":[{"value":"2024-01-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}