{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:57:24Z","timestamp":1774601844383,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031346187","type":"print"},{"value":"9783031346194","type":"electronic"}],"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\/978-3-031-34619-4_28","type":"book-chapter","created":{"date-parts":[[2023,6,10]],"date-time":"2023-06-10T19:01:31Z","timestamp":1686423691000},"page":"344-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A Novel Bangla Spoken Numerals Recognition System Using Convolutional Neural Network"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7727-9503","authenticated-orcid":false,"given":"Ovishake","family":"Sen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pias","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Al-Mahmud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,11]]},"reference":[{"key":"28_CR1","unstructured":"12 benefits of speech to text. https:\/\/www.dataworxs.com.au\/12-benefits-speech-text. Accessed30 June 2021"},{"key":"28_CR2","unstructured":"Mel frequency cepstral coefficient (MFCC) tutorial. http:\/\/www.practicalcryptography.com\/miscellaneous\/machine-learning\/guide-mel-frequency-cepstral-coefficients-mfccs. Accessed 28 June 2021"},{"key":"28_CR3","unstructured":"Mel-frequency cepstrum. https:\/\/en.wikipedia.org\/wiki\/Mel-frequencycepstrum. Accessed 28 June 2021"},{"key":"28_CR4","unstructured":"speech recognition. https:\/\/searchcustomerexperience.techtarget.com\/definition\/speech-recognition. Accessed 30 June 2021"},{"issue":"9","key":"28_CR5","first-page":"38","volume":"149","author":"K Ahammad","year":"2016","unstructured":"Ahammad, K., Rahman, M.M.: Connected Bangla speech recognition using artificial neural network. Int. J. Comput. Appl. 149(9), 38\u201341 (2016)","journal-title":"Int. J. Comput. Appl."},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Ahmed, T., Wahid, M.F., Habib, M.A.: Implementation of Bangla speech recognition in voice input speech output (viso) calculator. In: 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), pp. 1\u20135. IEEE (2018)","DOI":"10.1109\/ICBSLP.2018.8554773"},{"key":"28_CR7","unstructured":"Ali, M.A., Hossain, M., Bhuiyan, M.N., et al.: Automatic speech recognition technique for bangla words. Int. J. Adv. Sci. Technol. 50 (2013)"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Chung, T.D., Drieberg, M., Hassan, M.F.B., Khalyasmaa, A.: End-to-end conversion speed analysis of an FPT. AI-based text-to-speech application. In: 2020 IEEE 2nd Global Conference on Life Sciences and Technologies (LifeTech), pp. 136\u2013139. IEEE (2020)","DOI":"10.1109\/LifeTech48969.2020.1570620448"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Gales, M., Young, S.: The application of hidden Markov models in speech recognition (2008)","DOI":"10.1561\/9781601981219"},{"key":"28_CR10","unstructured":"Graves, A., Beringer, N., Schmidhuber, J.: A comparison between spiking and differentiable recurrent neural networks on spoken digit recognition. In: The 23rd IASTED International Conference on Modelling, Identification, and Control (2004)"},{"issue":"5\u20136","key":"28_CR11","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5\u20136), 602\u2013610 (2005)","journal-title":"Neural Netw."},{"key":"28_CR12","unstructured":"Hasnat, M., Mowla, J., Khan, M., et al.: Isolated and continuous Bangla speech recognition: implementation, performance and application perspective (2007)"},{"key":"28_CR13","unstructured":"Hossain, S., Rahman, M., Ahmed, F., Dewan, M.: Bangla speech synthesis, analysis, and recognition: an overview. Proc, NCCPB (2004)"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Islam, J., Mubassira, M., Islam, M.R., Das, A.K.: A speech recognition system for Bengali language using recurrent neural network. In: 2019 IEEE 4th International Conference on Computer and Communication Systems (ICCCS), pp. 73\u201376. IEEE (2019)","DOI":"10.1109\/CCOMS.2019.8821629"},{"key":"28_CR15","unstructured":"Liu, T., Fang, S., Zhao, Y., Wang, P., Zhang, J.: Implementation of training convolutional neural networks. arXiv preprint arXiv:1506.01195 (2015)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Muhammad, G., Alotaibi, Y.A., Huda, M.N.: Automatic speech recognition for bangla digits. In: 2009 12th International Conference on Computers and Information Technology, pp. 379\u2013383. IEEE (2009)","DOI":"10.1109\/ICCIT.2009.5407267"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Nahid, M.M.H., Purkaystha, B., Islam, M.S.: Bengali speech recognition: a double layered LSTM-RNN approach. In: 2017 20th International Conference of Computer and Information Technology (ICCIT), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/ICCITECHN.2017.8281848"},{"key":"28_CR18","unstructured":"Netshiombo, D., Mokgonyane, T.B., Manamela, M.J., Modipa, T.I.: Spoken digit recognition system for an extremely under-resourced language"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Paul, A.K., Das, D., Kamal, M.M.: Bangla speech recognition system using LPC and ANN. In: 2009 Seventh International Conference on Advances in Pattern Recognition, pp. 171\u2013174. IEEE (2009)","DOI":"10.1109\/ICAPR.2009.80"},{"key":"28_CR21","series-title":"Lecture Notes in Electrical Engineering","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/978-981-15-8752-8_9","volume-title":"Advances in Electronics, Communication and Computing","author":"B Paul","year":"2021","unstructured":"Paul, B., Bera, S., Paul, R., Phadikar, S.: Bengali spoken numerals recognition by MFCC and GMM technique. In: Mallick, P.K., Bhoi, A.K., Chae, G.-S., Kalita, K. (eds.) Advances in Electronics, Communication and Computing. LNEE, vol. 709, pp. 85\u201396. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-15-8752-8_9"},{"issue":"4","key":"28_CR22","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1109\/PROC.1976.10158","volume":"64","author":"DR Reddy","year":"1976","unstructured":"Reddy, D.R.: Speech recognition by machine: a review. Proc. IEEE 64(4), 501\u2013531 (1976)","journal-title":"Proc. IEEE"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Renjith, S., Joseph, A., Anish Babu K.K.: Isolated digit recognition for Malayalam-an application perspective. In: 2013 International Conference on Control Communication and Computing (ICCC), pp. 190\u2013193. IEEE (2013)","DOI":"10.1109\/ICCC.2013.6731648"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Saxena, B., Wahi, C.: Hindi digits recognition system on speech data collected in different natural noise environments. In: International Conference on Computer Science, Engineering and Information Technology (CSITY 2015) February, pp. 14\u201315 (2015)","DOI":"10.5121\/csit.2015.50303"},{"key":"28_CR25","doi-asserted-by":"publisher","first-page":"38999","DOI":"10.1109\/ACCESS.2022.3165563","volume":"10","author":"O Sen","year":"2022","unstructured":"Sen, O., et al.: Bangla natural language processing: a comprehensive analysis of classical, machine learning, and deep learning based methods. IEEE Access 10, 38999\u201339044 (2022)","journal-title":"IEEE Access"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Sen, O., Roy, P., et al.: A convolutional neural network based approach to recognize Bangla spoken digits from speech signal. In: 2021 International Conference on Electronics, Communications and Information Technology (ICECIT), pp. 1\u20134. IEEE (2021)","DOI":"10.1109\/ICECIT54077.2021.9641322"},{"key":"28_CR27","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1016\/j.procs.2020.04.148","volume":"171","author":"R Sharmin","year":"2020","unstructured":"Sharmin, R., Rahut, S.K., Huq, M.R.: Bengali spoken digit classification: a deep learning approach using convolutional neural network. Procedia Comput. Sci. 171, 1381\u20131388 (2020)","journal-title":"Procedia Comput. Sci."},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Shuvo, M., Shahriyar, S.A., Akhand, M.: Bangla numeral recognition from speech signal using convolutional neural network. In: 2019 International Conference on Bangla Speech and Language Processing (ICBSLP), pp. 1\u20134. IEEE (2019)","DOI":"10.1109\/ICBSLP47725.2019.201540"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Sultana, S., Akhand, M., Das, P.K., Rahman, M.H.: Bangla speech-to-text conversion using SAPI. In: 2012 International Conference on Computer and Communication Engineering (ICCCE), pp. 385\u2013390. IEEE (2012)","DOI":"10.1109\/ICCCE.2012.6271216"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Sumit, S.H., Al Muntasir, T., Zaman, M.A., Nandi, R.N., Sourov, T.: Noise robust end-to-end speech recognition for Bangla language. In: 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), pp. 1\u20135. IEEE (2018)","DOI":"10.1109\/ICBSLP.2018.8554871"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Sumon, S.A., Chowdhury, J., Debnath, S., Mohammed, N., Momen, S.: Bangla short speech commands recognition using convolutional neural networks. In: 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/ICBSLP.2018.8554395"},{"key":"28_CR32","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1016\/j.procs.2021.01.029","volume":"179","author":"D Taufik","year":"2021","unstructured":"Taufik, D., Hanafiah, N.: Autovat: an automated visual acuity test using spoken digit recognition with MEL frequency cepstral coefficients and convolutional neural network. Procedia Comput. Sci. 179, 458\u2013467 (2021)","journal-title":"Procedia Comput. Sci."}],"container-title":["Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","Machine Intelligence and Emerging Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-34619-4_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T02:37:09Z","timestamp":1729564629000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-34619-4_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031346187","9783031346194"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-34619-4_28","relation":{},"ISSN":["1867-8211","1867-822X"],"issn-type":[{"value":"1867-8211","type":"print"},{"value":"1867-822X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"11 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MIET","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Intelligence and Emerging Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Noakhali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangladesh","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miet2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/confmiet.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Confy plus","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"272","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"104","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}