{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T18:10:12Z","timestamp":1756663812361,"version":"3.44.0"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031983597","type":"print"},{"value":"9783031983603","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-031-98360-3_18","type":"book-chapter","created":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T17:40:00Z","timestamp":1756662000000},"page":"229-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech to Text Recognition by Machine Learning"],"prefix":"10.1007","author":[{"given":"S.","family":"Anitha Jebamani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Punitha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"V.","family":"Saraswathi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Swathyraja","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Kaviyarasan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,1]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1007\/s10772-024-10150-4","volume":"27","author":"M Tiwari","year":"2024","unstructured":"Tiwari, M., Verma, D.K.: Enhanced text-independent speaker recognition using MFCC, Bi-LSTM, and CNN-based noise removal techniques. Int. J. Speech Technol. 27, 1013\u20131026 (2024). https:\/\/doi.org\/10.1007\/s10772-024-10150-4","journal-title":"Int. J. Speech Technol."},{"key":"18_CR2","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s13636-024-00359-1","volume":"2024","author":"X Feng","year":"2024","unstructured":"Feng, X., Zhao, Y., Zong, W., et al.: Adaptive multi-task learning for speech to text translation. J. Audio Speech Music Proc. 2024, 36 (2024). https:\/\/doi.org\/10.1186\/s13636-024-00359-1","journal-title":"J. Audio Speech Music Proc."},{"key":"18_CR3","doi-asserted-by":"publisher","unstructured":"Garg, H., Dubey, P., Gupta, S., Jain, R.: Real-time conversion for sign-to-text and text-to-speech communication using machine learning. In: Yadav, A., Joshi, A.M., Ergezer, M., Balas, V.E. (eds.) Artificial Intelligence and Applications. ICAIA 2024. Algorithms for Intelligent Systems. Springer, Singapore (2025). https:\/\/doi.org\/10.1007\/978-981-97-8074-7_7","DOI":"10.1007\/978-981-97-8074-7_7"},{"key":"18_CR4","doi-asserted-by":"publisher","first-page":"73427","DOI":"10.1007\/s11042-023-17769-6","volume":"83","author":"S Tyagi","year":"2024","unstructured":"Tyagi, S., Sz\u00e9n\u00e1si, S.: Semantic speech analysis using machine learning and deep learning techniques: a comprehensive review. Multimed. Tools Appl. 83, 73427\u201373456 (2024). https:\/\/doi.org\/10.1007\/s11042-023-17769-6","journal-title":"Multimed. Tools Appl."},{"key":"18_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s13198-023-02143-4","author":"Y Xie","year":"2023","unstructured":"Xie, Y.: Application of speech recognition technology based on machine learning for network oral English teaching system. Int. J. Syst. Assur. Eng. Manag. (2023). https:\/\/doi.org\/10.1007\/s13198-023-02143-4","journal-title":"Int. J. Syst. Assur. Eng. Manag."},{"key":"18_CR6","doi-asserted-by":"publisher","first-page":"64205","DOI":"10.1007\/s11042-024-18121-2","volume":"83","author":"O Nazir","year":"2024","unstructured":"Nazir, O., Malik, A., Singh, S., et al.: Multi speaker text-to-speech synthesis using generalized end-to-end loss function. Multimed. Tools Appl. 83, 64205\u201364222 (2024). https:\/\/doi.org\/10.1007\/s11042-024-18121-2","journal-title":"Multimed. Tools Appl."},{"key":"18_CR7","doi-asserted-by":"publisher","first-page":"47069","DOI":"10.1007\/s11042-023-17368-5","volume":"83","author":"MK Singh","year":"2024","unstructured":"Singh, M.K.: Feature extraction and classification efficiency analysis using machine learning approach for speech signal. Multimed. Tools Appl. 83, 47069\u201347084 (2024). https:\/\/doi.org\/10.1007\/s11042-023-17368-5","journal-title":"Multimed. Tools Appl."},{"key":"18_CR8","doi-asserted-by":"publisher","unstructured":"Kumar, S., Vignesh Prabhu, P., Bhat, M.S., Kumar, S., Shubha, B.: Text detection and recognition using machine learning. In: Thirunavukkarasu, I., Kumar, R. (eds.) Control and Information Sciences. CISCON 2023. LNEE, vol. 1236. Springer, Singapore(2024). https:\/\/doi.org\/10.1007\/978-981-97-5866-1_28","DOI":"10.1007\/978"},{"key":"18_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-024-09540-2","author":"P Garg","year":"2024","unstructured":"Garg, P., Sharma, M.K., Kumar, P.: Improving hate speech classification through ensemble learning and explainable AI techniques. Arab. J. Sci. Eng. (2024). https:\/\/doi.org\/10.1007\/s13369-024-09540-2","journal-title":"Arab. J. Sci. Eng."},{"key":"18_CR10","doi-asserted-by":"publisher","first-page":"42763","DOI":"10.1007\/s11042-023-15275-3","volume":"82","author":"SK Panda","year":"2023","unstructured":"Panda, S.K., Jena, A.K., Panda, M.R., et al.: Speech emotion recognition using multimodal feature fusion with machine learning approach. Multimed. Tools Appl. 82, 42763\u201342781 (2023). https:\/\/doi.org\/10.1007\/s11042-023-15275-3","journal-title":"Multimed. Tools Appl."},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Janokar, S., Ratnaparkhi, S., Rathi, M., Rathod, A.: Text-to-speech and speech-to-text converter\u2014voice assistant. In: Suma, V., Lorenz, P., Baig, Z. (eds.) Inventive Systems and Control. Lecture Notes in Networks and Systems, vol. 672. Springer, Singapore (2023). https:\/\/doi.org\/10.1007\/978-981-99-1624-5_48","DOI":"10.1007\/978-981-99-1624-5_48"},{"key":"18_CR12","doi-asserted-by":"publisher","unstructured":"Saulitis, K., Urtans, E., Caune, V.: Towards natural-sounding speech to text in english. In: Fred, A., Hadjali, A., Gusikhin, O., Sansone, C. (eds.) Deep Learning Theory and Applications. DeLTA 2024. Communications in Computer and Information Science, vol. 2171. Springer, Cham (2024), https:\/\/doi.org\/10.1007\/978-3-031-66694-0_5","DOI":"10.1007\/978-3"}],"container-title":["IFIP Advances in Information and Communication Technology","Computational Intelligence in Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-98360-3_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T17:40:00Z","timestamp":1756662000000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-98360-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"ISBN":["9783031983597","9783031983603"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-98360-3_18","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"value":"1868-4238","type":"print"},{"value":"1868-422X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,1]]},"assertion":[{"value":"1 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Intelligence in Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chennai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 February 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 February 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccids2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccids.in\/ICCIDS2025\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}