{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:46:16Z","timestamp":1758127576530,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819967056"},{"type":"electronic","value":"9789819967063"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-6706-3_9","type":"book-chapter","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T11:02:34Z","timestamp":1700910154000},"page":"97-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Systematic Review on Automatic Speech Recognition for Odia Language"],"prefix":"10.1007","author":[{"given":"Namita","family":"Mishra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satya Ranjan","family":"Dash","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shantipriya","family":"Parida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ravi Shankar","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"key":"9_CR1","unstructured":"Speech Dataset Creation: https:\/\/ogunlao.github.io\/blog\/2021\/01\/26\/how-to-create-speech-dataset"},{"issue":"3","key":"9_CR2","first-page":"16","volume":"10","author":"SK Gaikwad","year":"2010","unstructured":"Gaikwad, S.K., Gawali, B.W., Yannawar, P.: A review on speech recognition technique. Int. J. Comput. Appl. 10(3), 16\u201324 (2010)","journal-title":"Int. J. Comput. Appl."},{"key":"9_CR3","unstructured":"Forsberg, M.: Why is Speech Recognition Difficult.\u00a0Chalmers University of Technology (2003)"},{"key":"9_CR4","unstructured":"Speech Processing: https:\/\/en.wikipedia.org\/wiki\/Speech_processin"},{"key":"9_CR5","unstructured":"Speech Synthesis: Wikipedia"},{"key":"9_CR6","unstructured":"Voice Activity Detection: https:\/\/en.wikipedia.org\/wiki\/Voice_activity_detection"},{"key":"9_CR7","unstructured":"Shrawankar, U., Thakare, V.M.: Techniques for Feature Extraction in Speech Recognition System: A Comparative Study (2013). arXiv preprint arXiv:1305.1145"},{"issue":"1","key":"9_CR8","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/TASSP.1975.1162641","volume":"23","author":"F Itakura","year":"1975","unstructured":"Itakura, F.: Minimum prediction residual principle applied to speech recognition. IEEE Trans. Acoust. Speech Signal Process. 23(1), 67\u201372 (1975)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"9_CR9","unstructured":"Rabiner, L., Juang, B.H.:\u00a0Fundamentals of Speech Recognition. Prentice-Hall, Inc (1993)"},{"issue":"4","key":"9_CR10","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357\u2013366 (1980)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Mohanty, S., Swain, B.K.: Speech input-output system in Indian farming sector. In: 2012 IEEE International Conference on Computational Intelligence and Computing Research, pp. 1\u20135. IEEE (2012)","DOI":"10.1109\/ICCIC.2012.6510195"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Fan, Y., Sun-Hua, X., Ming-Hui, L., Guo-Feng, P.: Research on a new method of preprocessing and speech synthesis pitch detection. In: 2010 International Conference on Computer Design and Applications,\u00a0vol. 1, pp. V1\u2013399. IEEE (2010)","DOI":"10.1109\/ICCDA.2010.5540832"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Berdibaeva, G.K., Bodin, O.N., Kozlov, V.V., Nefed\u2019ev, D.I., Ozhikenov, K.A., Pizhonkov, Y.A.: Pre-processing voice signals for voice recognition systems. In: 2017 18th International Conference of Young Specialists on Micro\/Nanotechnologies and Electron Devices (EDM), pp. 242\u2013245. IEEE (2017)","DOI":"10.1109\/EDM.2017.7981748"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Georgescu, A.L., Cucu, H.: Automatic annotation of speech corpora using complementary GMM and DNN acoustic models. In: 2018 41st International Conference on Telecommunications and Signal Processing (TSP), pp. 1\u20134. IEEE (2018)","DOI":"10.1109\/TSP.2018.8441374"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Rajasekhar, A., Hota, M.K.: A study of speech, speaker and emotion recognition using Mel frequency cepstrum coefficients and support vector machines. In: 2018 International Conference on Communication and Signal Processing (ICCSP), pp. 0114\u20130118. IEEE (2018)","DOI":"10.1109\/ICCSP.2018.8524451"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Eray, O., Tokat, S., Iplikci, S.: An application of speech recognition with support vector machines. In: 2018 6th International Symposium on Digital Forensic and Security (ISDFS), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/ISDFS.2018.8355321"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Feng, X., Zhang, Y., Glass, J.: Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1759\u20131763. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6853900"},{"issue":"6","key":"9_CR18","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"9_CR19","unstructured":"Maas, A.L., O\u2019Neil, T.M., Hannun, A.Y., Ng, A.Y.: Recurrent neural network feature enhancement: the 2nd CHiME challenge. In: Proceedings the 2nd CHiME Workshop on Machine Listening in Multisource Environments Held in Conjunction with ICASSP, pp. 79\u201380 (2013)"},{"issue":"1","key":"9_CR20","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2011","unstructured":"Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30\u201342 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"1","key":"9_CR21","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","volume":"20","author":"AR Mohamed","year":"2011","unstructured":"Mohamed, A.R., Dahl, G.E., Hinton, G.: Acoustic modeling using deep belief networks. IEEE Trans. Audio Speech Lang. Process. 20(1), 14\u201322 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Bourlard, H.A., Morgan, N.:\u00a0Connectionist Speech Recognition: A Hybrid Approach, vol. 247. Springer Science & Business Media (1994)","DOI":"10.1007\/978-1-4615-3210-1"},{"issue":"1","key":"9_CR23","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1109\/89.260359","volume":"2","author":"S Renals","year":"1994","unstructured":"Renals, S., Morgan, N., Bourlard, H., Cohen, M., Franco, H.: Connectionist probability estimators in HMM speech recognition. IEEE Trans. Speech and Audio Process. 2(1), 161\u2013174 (1994)","journal-title":"IEEE Trans. Speech and Audio Process."},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Ramabhadran, B.: Auto-encoder bottleneck features using deep belief networks. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4153\u20134156. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6288833"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096\u20131103 (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"9_CR26","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A., Bottou, L.: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res.\u00a011(12) (2010)"},{"key":"9_CR27","unstructured":"Lan, Y., Theobald, B.J., Harvey, R., Ong, E.J., Bowden, R.: Improving visual features for lip-reading. In: Auditory-Visual Speech Processing 2010 (2010)"},{"issue":"2","key":"9_CR28","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/34.982900","volume":"24","author":"I Matthews","year":"2002","unstructured":"Matthews, I., Cootes, T., Bangham, J., Cox, S., Harvey, R.: Extraction of visual features for lipreading. IEEE Trans. Pattern Anal. Mach. Intell. 24(2), 198\u2013213 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Luettin, J., Thacker, N.A., Beet, S.W.: Visual speech recognition using active shape models and hidden Markov models. In: 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings, vol. 2, pp. 817\u2013820. IEEE (1996)","DOI":"10.1109\/ICASSP.1996.543246"},{"issue":"6","key":"9_CR30","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1109\/34.927467","volume":"23","author":"TF Cootes","year":"2001","unstructured":"Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. 23(6), 681\u2013685 (2001)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Matthews, I., Potamianos, G., Neti, C., Luettin, J.: A comparison of model and transform-based visual features for audio-visual LVCSR. In: IEEE International Conference on Multimedia and Expo, pp. 210\u2013210. IEEE Computer Society (2001)","DOI":"10.1109\/ICME.2001.1237849"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Droua-Hamdani, G., Sellouani, S.A., Boudraa, M.: Effect of characteristics of speakers on MSA ASR performance. In: 2013 1st International Conference on Communications, Signal Processing, and their Applications (ICCSPA), pp. 1\u20135. IEEE (2013)","DOI":"10.1109\/ICCSPA.2013.6487262"}],"container-title":["Smart Innovation, Systems and Technologies","Intelligent Data Engineering and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-6706-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T09:42:06Z","timestamp":1730626926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-6706-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819967056","9789819967063"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-6706-3_9","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"type":"print","value":"2190-3018"},{"type":"electronic","value":"2190-3026"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"26 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FICTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Frontiers of Intelligent Computing: Theory and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cardiff","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ficta2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ficta.co.uk\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}