{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T22:22:15Z","timestamp":1780352535407,"version":"3.54.1"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T00:00:00Z","timestamp":1734566400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T00:00:00Z","timestamp":1734566400000},"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":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s00034-024-02950-5","type":"journal-article","created":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T17:51:58Z","timestamp":1734630718000},"page":"2855-2881","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Real-Time Continuous Tamil Dialect Speech Recognition and Summarization"],"prefix":"10.1007","volume":"44","author":[{"given":"S.","family":"Saranya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7279-5357","authenticated-orcid":false,"given":"B.","family":"Bharathi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.","family":"Gomathy Dhanya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aishwarya","family":"Krishnakumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,19]]},"reference":[{"key":"2950_CR1","doi-asserted-by":"crossref","unstructured":"A. Akhilesh, P. Brinda, S. Keerthana, D. Gupta, S. Vekkot, Tamil speech recognition using xlsr wav2vec2. 0 & ctc algorithm. In: 2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT), IEEE, pp 1\u20136 (2022)","DOI":"10.1109\/ICCCNT54827.2022.9984422"},{"issue":"27","key":"2950_CR2","doi-asserted-by":"publisher","first-page":"42783","DOI":"10.1007\/s11042-023-15413-x","volume":"82","author":"MJ Al Dujaili","year":"2023","unstructured":"M.J. Al Dujaili, A. Ebrahimi-Moghadam, Automatic speech emotion recognition based on hybrid features with ann, lda and k_nn classifiers. Multimedia Tools Appl. 82(27), 42783\u201342801 (2023)","journal-title":"Multimedia Tools Appl."},{"key":"2950_CR3","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","unstructured":"A. Baevski, Y. Zhou, A. Mohamed, M. Auli, wav2vec 2.0: A framework for self-supervised learning of speech representations. Adv. Neural. Inf. Process. Syst. 33, 12449\u201312460 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2950_CR4","doi-asserted-by":"crossref","unstructured":"E. Battenberg, J. Chen, R. Child, A. Coates, Y.G.Y. Li, H. Liu, S. Satheesh, A. Sriram, Z. Zhu, Exploring neural transducers for end-to-end speech recognition. In: 2017 IEEE automatic speech recognition and understanding workshop (ASRU), IEEE, pp 206\u2013213 (2017)","DOI":"10.1109\/ASRU.2017.8268937"},{"key":"2950_CR5","doi-asserted-by":"crossref","unstructured":"A. Bhattacharjee, T. Hasan, W.U. Ahmad, Y.F. Li, Y.B. Kang, R. Shahriyar, Crosssum: Beyond english-centric cross-lingual summarization for 1,500+ language pairs. In: Annual Meeting of the Association of Computational Linguistics 2023, Association for Computational Linguistics (ACL), pp 2541\u20132564 (2023)","DOI":"10.18653\/v1\/2023.acl-long.143"},{"key":"2950_CR6","doi-asserted-by":"crossref","unstructured":"S. Chattopadhyay, J.H. Bhat, S. Rasipuram, A. Debsharma, A. Maitra, Improving performance of nemo asr system for indian accent english. In: 2022 IEEE 19th India Council International Conference (INDICON), IEEE, pp 1\u20135 (2022)","DOI":"10.1109\/INDICON56171.2022.10039815"},{"key":"2950_CR7","doi-asserted-by":"crossref","unstructured":"Graves, A. Sequence transduction with recurrent neural networks. arXiv preprint arXiv:1211.3711 (2012)","DOI":"10.1007\/978-3-642-24797-2"},{"key":"2950_CR8","doi-asserted-by":"crossref","unstructured":"A. Graves, S. Fern\u00e1ndez, F. Gomez, J. Schmidhuber, Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd international conference on Machine learning, pp 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"2950_CR9","doi-asserted-by":"crossref","unstructured":"S. Kriman, S. Beliaev, B. Ginsburg, J. Huang, O. Kuchaiev, V. Lavrukhin, R. Leary, J. Li, Y. Zhang, Quartznet: Deep automatic speech recognition with 1d time-channel separable convolutions. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics. (Speech and Signal Processing (ICASSP), IEEE, 2020), pp.6124\u20136128","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"2950_CR10","doi-asserted-by":"crossref","unstructured":"J. Luo, J. Wang, N. Cheng, E. Xiao, J. Xiao, G. Kucsko, P. O\u2019Neill, J. Balam, S. Deng, A. Flores, et\u00a0al., Cross-language transfer learning and domain adaptation for end-to-end automatic speech recognition. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), IEEE, pp 1\u20136 (2021)","DOI":"10.1109\/ICME51207.2021.9428334"},{"key":"2950_CR11","doi-asserted-by":"crossref","unstructured":"J. Mahadeokar, Y. Shangguan, D. Le, G. Keren, H. Su, T. Le, C.F. Yeh, C. Fuegen, M.L. Seltzer, Alignment restricted streaming recurrent neural network transducer. In: 2021 IEEE Spoken Language Technology Workshop (SLT), IEEE, pp 52\u201359 (2021)","DOI":"10.1109\/SLT48900.2021.9383606"},{"key":"2950_CR12","unstructured":"A. Radford, J.W. Kim, T. Xu, G. Brockman, C. McLeavey, I. Sutskever, Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, PMLR, pp 28492\u201328518 (2023)"},{"key":"2950_CR13","unstructured":"H. Shao, W. Wang, B. Liu, X. Gong, H. Wang, Y. Qian, Whisper-kdq: A lightweight whisper via guided knowledge distillation and quantization for efficient asr. arXiv preprint arXiv:2305.10788 (2023)"},{"key":"2950_CR14","doi-asserted-by":"crossref","unstructured":"Y. Shi, Y. Wang, C. Wu, C.F. Yeh, J. Chan, F. Zhang, D. Le, M. Seltzer, Emformer: Efficient memory transformer based acoustic model for low latency streaming speech recognition. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics. (Speech and Signal Processing (ICASSP), IEEE, 2021), pp.6783\u20136787","DOI":"10.1109\/ICASSP39728.2021.9414560"},{"key":"2950_CR15","doi-asserted-by":"crossref","unstructured":"L. Xue, N. Constant, A. Roberts, M. Kale, R. Al-Rfou, A. Siddhant, A. Barua, C. Raffel, mt5: A massively multilingual pre-trained text-to-text transformer. arXiv preprint arXiv:2010.11934 (2020)","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"2950_CR16","doi-asserted-by":"crossref","unstructured":"Y. Yang, Y. Li, B. Du, Improving ctc-based asr models with gated interlayer collaboration. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics. (Speech and Signal Processing (ICASSP), IEEE, 2023), pp.1\u20135","DOI":"10.1109\/ICASSP49357.2023.10094820"},{"key":"2950_CR17","doi-asserted-by":"crossref","unstructured":"Q. Zhang, H. Lu, H. Sak, A. Tripathi, E. McDermott, S. Koo, S. Kumar, Transformer transducer: A streamable speech recognition model with transformer encoders and rnn-t loss. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics. (Speech and Signal Processing (ICASSP), IEEE, 2020), pp.7829\u20137833","DOI":"10.1109\/ICASSP40776.2020.9053896"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02950-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-024-02950-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02950-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T16:21:18Z","timestamp":1742314878000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-024-02950-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,19]]},"references-count":17,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["2950"],"URL":"https:\/\/doi.org\/10.1007\/s00034-024-02950-5","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,19]]},"assertion":[{"value":"29 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 November 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2024","order":4,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}