{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T08:28:21Z","timestamp":1743323301229,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T00:00:00Z","timestamp":1606262400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T00:00:00Z","timestamp":1606262400000},"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":[[2023,3]]},"DOI":"10.1007\/s10772-020-09769-w","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T16:05:54Z","timestamp":1606320354000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Exploration of diverse intelligent approaches in speech recognition systems"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0452-4608","authenticated-orcid":false,"given":"Iwin Thanakumar Joseph","family":"Swamidason","sequence":"first","affiliation":[]},{"given":"Sravanthi","family":"Tatiparthi","sequence":"additional","affiliation":[]},{"given":"V. M.","family":"Arul Xavier","sequence":"additional","affiliation":[]},{"given":"C. S. C.","family":"Devadass","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,25]]},"reference":[{"key":"9769_CR1","unstructured":"Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., Chen, G., & Chen, J. (2016, June). Deep speech 2: End-to-end speech recognition in english and mandarin. In International conference on machine learning (pp. 173\u2013182)."},{"key":"9769_CR2","doi-asserted-by":"publisher","first-page":"85327","DOI":"10.1109\/ACCESS.2019.2917470","volume":"7","author":"NN An","year":"2019","unstructured":"An, N. N., Thanh, N. Q., & Liu, Y. (2019). Deep CNNs with self-attention for speaker identification. IEEE Access, 7, 85327\u201385337.","journal-title":"IEEE Access"},{"key":"9769_CR3","doi-asserted-by":"crossref","unstructured":"Blunt, P., & Haskins, B. (2019, November). A model for incorporating an automatic speech recognition system in a noisy educational environment. In 2019 International multidisciplinary information technology and engineering conference (IMITEC) (pp. 1\u20137). IEEE.","DOI":"10.1109\/IMITEC45504.2019.9015907"},{"key":"9769_CR4","unstructured":"Brems, D. J., & Schoeffler, M. S. (1996). U.S. Patent No. 5,566,272. Washington, DC: U.S. Patent and Trademark Office."},{"key":"9769_CR5","doi-asserted-by":"publisher","first-page":"2","DOI":"10.18178\/ijmlc.2019.9.2.778","volume":"9","author":"S Bunrit","year":"2019","unstructured":"Bunrit, S., et al. (2019). Text-independent speaker identification using deep learning model of convolution neural network. International Journal of Machine Learning and Computing, 9, 2.","journal-title":"International Journal of Machine Learning and Computing"},{"issue":"5","key":"9769_CR6","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1109\/TASL.2013.2244083","volume":"21","author":"L Deng","year":"2013","unstructured":"Deng, L., & Li, X. (2013). Machine learning paradigms for speech recognition: An overview. IEEE Transactions on Audio, Speech and Language Processing, 21(5), 1060\u20131089.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9769_CR7","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. 2013 IEEE international conference on acoustics, speech and signal processing. IEEE.","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"9769_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, K., & Gupta, D. (2016, January). An analysis on LPC, RASTA and MFCC techniques in Automatic Speech recognition system. In 2016 6th international conference-cloud system and big data engineering (confluence) (pp. 493\u2013497). IEEE.","DOI":"10.1109\/CONFLUENCE.2016.7508170"},{"key":"9769_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Patel, N., & Khan, S. (2014, November). Automatic speech recognition technique for voice command. In 2014 international conference on science engineering and management research (ICSEMR) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ICSEMR.2014.7043641"},{"key":"9769_CR10","doi-asserted-by":"crossref","unstructured":"Kavitha, S., Veena, S., & Kumaraswamy, R. (2015, December). Development of automatic speech recognition system for voice activated Ground Control system. In 2015 international conference on trends in automation, communications and computing technology (I-TACT-15) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ITACT.2015.7492684"},{"key":"9769_CR11","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/j.csl.2017.04.003","volume":"45","author":"A Khosravani","year":"2017","unstructured":"Khosravani, A., & Homayounpour, M. M. (2017). A PLDA approach for language and text independent speaker recognition. Computer Speech & Language, 45, 457\u2013474.","journal-title":"Computer Speech & Language"},{"key":"9769_CR12","doi-asserted-by":"crossref","unstructured":"Koo, M. W., Choi, J. K., & Kim, Y. M. (2008, February). The development of automatic speech recognition software for portable devices. In First international conference on advances in computer\u2013human interaction (pp. 59\u201362). IEEE.","DOI":"10.1109\/ACHI.2008.44"},{"key":"9769_CR13","doi-asserted-by":"crossref","unstructured":"Kumar, Y., & Singh, N. (2019, April). A comprehensive view of automatic speech recognition system-A systematic literature review. In 2019 international conference on automation, computational and technology management (ICACTM) (pp. 168\u2013173). IEEE.","DOI":"10.1109\/ICACTM.2019.8776714"},{"key":"9769_CR14","doi-asserted-by":"crossref","unstructured":"Lee, T., Liu, Y., Huang, P. W., Chien, J. T., Lam, W. K., Yeung, Y. T\u2026. Law, S. P. (2016, March). Automatic speech recognition for acoustical analysis and assessment of cantonese pathological voice and speech. In 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 6475\u20136479). IEEE.","DOI":"10.1109\/ICASSP.2016.7472924"},{"key":"9769_CR15","doi-asserted-by":"crossref","unstructured":"Londhe, N. D., Ahirwal, M. K., & Lodha, P. (2016, April). Machine learning paradigms for speech recognition of an Indian dialect. In 2016 international conference on communication and signal processing (ICCSP) (pp. 0780\u20130786). IEEE.","DOI":"10.1109\/ICCSP.2016.7754251"},{"key":"9769_CR16","unstructured":"Makhmudov, A. Z., & Abdukarimov, S. S. (2016). Speech recognition using deep learning algorithms. \u0418\u043d\u0444op\u043ca\u0442\u0438\u043aa: \u043fpo\u0431\u043be\u043c\u044b, \u043ce\u0442o\u0434o\u043bo\u0433\u0438\u044f, \u0442ex\u043do\u043bo\u0433\u0438\u0438."},{"key":"9769_CR17","doi-asserted-by":"crossref","unstructured":"Mokgonyane, T. B., Sefara, T. J., Modipa, T. I., Mogale, M. M., Manamela, M. J., & Manamela, P. J. (2019, January). Automatic speaker recognition system based on machine learning algorithms. In 2019 Southern African Universities Power Engineering Conference\/Robotics and Mechatronics\/Pattern Recognition Association of South Africa (SAUPEC\/RobMech\/PRASA) (pp. 141\u2013146). IEEE.","DOI":"10.1109\/RoboMech.2019.8704837"},{"key":"9769_CR18","doi-asserted-by":"publisher","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","volume":"7","author":"AB Nassif","year":"2019","unstructured":"Nassif, A. B., Shahin, I., Attili, I., Azzeh, M., & Shaalan, K. (2019). Speech recognition using deep neural networks: A systematic review. IEEE Access, 7, 19143\u201319165.","journal-title":"IEEE Access"},{"key":"9769_CR19","unstructured":"Park, J., Boo, Y., Choi, I., Shin, S., & Sung, W. (2018). Fully neural network based speech recognition on mobile and embedded devices. In Advances in neural information processing systems (pp. 10620\u201310630)."},{"key":"9769_CR20","doi-asserted-by":"crossref","unstructured":"Pramanik, A., & Raha, R. (2012, October). Automatic speech recognition using correlation analysis. In 2012 World congress on information and communication technologies (pp. 670\u2013674). IEEE.","DOI":"10.1109\/WICT.2012.6409160"},{"issue":"10","key":"9769_CR21","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1109\/LSP.2015.2420092","volume":"22","author":"F Richardson","year":"2015","unstructured":"Richardson, F., Reynolds, D., & Dehak, N. (2015). Deep neural network approaches to speaker and language recognition. IEEE Signal Processing Letters, 22(10), 1671\u20131675.","journal-title":"IEEE Signal Processing Letters"},{"issue":"5","key":"9769_CR22","first-page":"1017","volume":"4","author":"CR Rubi","year":"2015","unstructured":"Rubi, C. R. (2015). A review: Speech recognition with deep learning methods. International Journal of Computer Science and Mobile Computing, 4(5), 1017\u20131024.","journal-title":"International Journal of Computer Science and Mobile Computing"},{"key":"9769_CR23","doi-asserted-by":"crossref","unstructured":"Sahu, P. K., & Ganesh, D. S. (2015, December). A study on automatic speech recognition toolkits. In 2015 international conference on microwave, optical and communication engineering (ICMOCE) (pp. 365\u2013368). IEEE.","DOI":"10.1109\/ICMOCE.2015.7489768"},{"key":"9769_CR24","unstructured":"Song, W., & Cai, J. (2015). End-to-end deep neural network for automatic speech recognition. Standford CS224D Reports."},{"key":"9769_CR25","unstructured":"Sztah\u00f3, D., Szasz\u00e1k, G., & Beke, A. (2019). Deep learning methods in speaker recognition: A review. arXiv:1911.06615."},{"key":"9769_CR26","doi-asserted-by":"crossref","unstructured":"Tirumala, S. S., & Shahamiri, S. R. (2016, November). A review on Deep Learning approaches in Speaker Identification. In Proceedings of the 8th international conference on signal processing systems (pp. 142\u2013147).","DOI":"10.1145\/3015166.3015210"},{"issue":"2","key":"9769_CR27","first-page":"39","volume":"20","author":"A Trivedi","year":"2018","unstructured":"Trivedi, A., et al. (2018). Speech to text and text to speech recognition systems-A review. IOSR Journal of Computer Engineering, 20(2), 39.","journal-title":"IOSR Journal of Computer Engineering"},{"key":"9769_CR28","doi-asserted-by":"crossref","unstructured":"Valin, J. M. (2018, August). A hybrid DSP\/deep learning approach to real-time full-band speech enhancement. In 2018 IEEE 20th international workshop on multimedia signal processing (MMSP) (pp. 1\u20135). IEEE.","DOI":"10.1109\/MMSP.2018.8547084"},{"key":"9769_CR29","doi-asserted-by":"crossref","unstructured":"Variani, E., Lei, X., McDermott, E., Moreno, I. L., & Gonzalez-Dominguez, J. (2014). Deep neural networks for small footprint text-dependent speaker verification. In 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP), (pp. 4052\u20134056). IEEE.","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"9769_CR30","unstructured":"Wu, C. (2018). Structured deep neural networks for speech recognition. PhD diss., University of Cambridge."},{"issue":"5","key":"9769_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3178115","volume":"9","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Geiger, J., Pohjalainen, J., Mousa, A. E. D., Jin, W., & Schuller, B. (2018). Deep learning for environmentally robust speech recognition: An overview of recent developments. ACM Transactions on Intelligent Systems and Technology (TIST), 9(5), 1\u201328.","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09769-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-020-09769-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09769-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T11:10:48Z","timestamp":1679915448000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-020-09769-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,25]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["9769"],"URL":"https:\/\/doi.org\/10.1007\/s10772-020-09769-w","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2020,11,25]]},"assertion":[{"value":"4 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Authors declared no conflict of Interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}