{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T11:38:30Z","timestamp":1781609910273,"version":"3.54.5"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030822682","type":"print"},{"value":"9783030822699","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-82269-9_29","type":"book-chapter","created":{"date-parts":[[2021,7,27]],"date-time":"2021-07-27T08:02:48Z","timestamp":1627372968000},"page":"371-383","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Mixed Bangla-English Spoken Digit Classification Using Convolutional Neural Network"],"prefix":"10.1007","author":[{"given":"Shuvro","family":"Das","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mst. Rubayat","family":"Yasmin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Musfikul","family":"Arefin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazi Abu","family":"Taher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Nasir","family":"Uddin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Arifur","family":"Rahman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,26]]},"reference":[{"key":"29_CR1","first-page":"80","volume":"1","author":"FI Adiba","year":"2020","unstructured":"Adiba, F.I., Islam, T., Kaiser, M.S., Mahmud, M., Rahman, M.A.: Effect of corpora on classification of fake news using naive bayes classifier. Int. J. Autom. AI Mach. Learn. Canada 1, 80\u201392 (2020)","journal-title":"Int. J. Autom. AI Mach. Learn. Canada"},{"key":"29_CR2","doi-asserted-by":"publisher","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 (2018). https:\/\/doi.org\/10.1109\/ICBSLP.2018.8554395","DOI":"10.1109\/ICBSLP.2018.8554395"},{"key":"29_CR3","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: SoundNet: learning sound representations from unlabeled video. CoRR abs\/1610.09001 (2016). http:\/\/arxiv.org\/abs\/1610.09001"},{"key":"29_CR4","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)"},{"key":"29_CR5","unstructured":"Blog, G.A.: Launching the speech commands dataset, August 2017. https:\/\/ai.googleblog.com\/2017\/08\/launching-speech-commands-dataset.html\/\/"},{"key":"29_CR6","unstructured":"Choi, K., Fazekas, G., Sandler, M.B., Cho, K.: Convolutional recurrent neural networks for music classification. CoRR abs\/1609.04243 (2016). http:\/\/arxiv.org\/abs\/1609.04243"},{"key":"29_CR7","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1007\/978-981-33-4673-4_50","volume-title":"Proceedings of International Conference on Trends in Computational and Cognitive Engineering","author":"TR Das","year":"2021","unstructured":"Das, T.R., Hasan, S., Sarwar, S.M., Das, J.K., Rahman, M.A.: Facial spoof detection using support vector machine. In: Kaiser, M.S., Bandyopadhyay, A., Mahmud, M., Ray, K. (eds.) Proceedings of International Conference on Trends in Computational and Cognitive Engineering. AISC, vol. 1309, pp. 615\u2013625. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-33-4673-4_50"},{"key":"29_CR8","doi-asserted-by":"publisher","first-page":"66529","DOI":"10.1109\/ACCESS.2020.2984903","volume":"8","author":"F Demir","year":"2020","unstructured":"Demir, F., Abdullah, D., Sengur, A.: A new deep CNN model for environmental sound classification. IEEE Access 8, 66529\u201366537 (2020)","journal-title":"IEEE Access"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Dong, M.: Convolutional neural network achieves human-level accuracy in music genre classification. CoRR abs\/1802.09697 (2018). http:\/\/arxiv.org\/abs\/1802.09697","DOI":"10.32470\/CCN.2018.1153-0"},{"key":"29_CR10","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/978-981-33-4673-4_51","volume-title":"Proceedings of International Conference on Trends in Computational and Cognitive Engineering","author":"H Ferdous","year":"2021","unstructured":"Ferdous, H., Siraj, T., Setu, S.J., Anwar, M.M., Rahman, M.A.: Machine learning approach towards satellite image classification. In: Kaiser, M.S., Bandyopadhyay, A., Mahmud, M., Ray, K. (eds.) Proceedings of International Conference on Trends in Computational and Cognitive Engineering. AISC, vol. 1309, pp. 627\u2013637. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-33-4673-4_51"},{"key":"29_CR11","unstructured":"getsmarter: Applications of speech recognition, March 2019. https:\/\/getsmarter.com\/blog\/market-trends\/ applications-of-speech-recognition\/\/"},{"key":"29_CR12","doi-asserted-by":"publisher","unstructured":"Ghanty, S., Shaikh, S., Chaki, N.: On recognition of spoken Bengali numerals. In: International Conference on Computer Information Systems and Industrial Management Applications (CISIM), pp. 54\u201359 (10 2010). https:\/\/doi.org\/10.1109\/CISIM.2010.5643692","DOI":"10.1109\/CISIM.2010.5643692"},{"issue":"2","key":"29_CR13","first-page":"263","volume":"15","author":"A Gupta","year":"2018","unstructured":"Gupta, A., Sarkar, K.: Recognition of spoken Bengali numerals using MLP, SVM, RF based models with PCA based feature summarization. Int. Arab J. Inf. Technol. 15(2), 263\u2013269 (2018)","journal-title":"Int. Arab J. Inf. Technol."},{"key":"29_CR14","unstructured":"Hees, A.G.F.R.J., Dengel, A.: EsresNet: environmental sound classification based on visual domain models. arXiv (2020)"},{"key":"29_CR15","doi-asserted-by":"publisher","first-page":"22","DOI":"10.5120\/ijca2016907827","volume":"133","author":"S Huque","year":"2016","unstructured":"Huque, S., Rasel, A., Islam, B.: Analysis of a small vocabulary Bangla speech database for recognition. Int. J. Comput. Appl. 133, 22\u201328 (2016). https:\/\/doi.org\/10.5120\/ijca2016907827","journal-title":"Int. J. Comput. Appl."},{"key":"29_CR16","first-page":"12","volume":"7","author":"H Mahalingam","year":"2019","unstructured":"Mahalingam, H., Rajakumar, M.: Speech recognition using multiscale scattering of audio signals and long short-term memory 0f neural networks. Int. J. Adv. Comput. Sci. Cloud Comput. 7, 12\u201316 (2019)","journal-title":"Int. J. Adv. Comput. Sci. Cloud Comput."},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Mahmud, M., Kaiser, M.S., Hussain, A.: Deep learning in mining biological data. arXiv (2021)","DOI":"10.1007\/s12559-020-09773-x"},{"key":"29_CR18","unstructured":"Mahmud, M., Kaiser, M.S., Hussain, A., Vassanelli, S.: Applications of deep learning and reinforcement learning to biological data. CoRR abs\/1711.03985 (2017). http:\/\/arxiv.org\/abs\/1711.03985"},{"key":"29_CR19","doi-asserted-by":"publisher","unstructured":"Muhammad, G., Alotaibi, Y., Huda, M.: Automatic speech recognition for Bangla digits. In: 12th International Conference on Computers and Information Technology, pp. 379\u2013383, January 2010. https:\/\/doi.org\/10.1109\/ICCIT.2009.5407267","DOI":"10.1109\/ICCIT.2009.5407267"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Nasrullah, Z., Zhao, Y.: Music artist classification with convolutional recurrent neural networks. In: International Joint Conference on Neural Networks (IJCNN), pp. 1381\u20131388 (2019)","DOI":"10.1109\/IJCNN.2019.8851988"},{"key":"29_CR21","unstructured":"van den Oord, A., et al..: WaveNet: a generative model for raw audio. CoRR abs\/1609.03499 (2016). http:\/\/arxiv.org\/abs\/1609.03499"},{"key":"29_CR22","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"},{"key":"29_CR23","unstructured":"PyPI: librosa.feature.mfcc librosa 0.8.0 documentation (www document) (2020). https:\/\/pypi.org\/project\/librosa\/"},{"key":"29_CR24","unstructured":"Rahman, M.A.: Gaussian process in computational biology: covariance functions for transcriptomics. Ph.D. thesis, University of Sheffield (2018)"},{"issue":"02","key":"29_CR25","first-page":"1468","volume":"29","author":"PVN Reddy","year":"2020","unstructured":"Reddy, P.V.N., Kumar, D.D.A.: Test accuracy improvement in spoken digit recognition using convolutional neural networks. Int. J. Adv. Sci. Technol. 29(02), 1468\u20131477 (2020)","journal-title":"Int. J. Adv. Sci. Technol."},{"key":"29_CR26","unstructured":"Roberts, A., Engel, J.H., Raffel, C., Hawthorne, C., Eck, D.: A hierarchical latent vector model for learning long-term structure in music. CoRR abs\/1803.05428 (2018). http:\/\/arxiv.org\/abs\/1803.05428"},{"key":"29_CR27","first-page":"1","volume":"1","author":"R Sadik","year":"2020","unstructured":"Sadik, R., Reza, M.L., Noman, A.A., Mamun, S.A., Kaiser, M.S., Rahman, M.A.: Covid-19 pandemic: a comparative prediction using machine learning. Int. J. Autom. AI Mach. Learn. Canada 1, 1\u201316 (2020)","journal-title":"Int. J. Autom. AI Mach. Learn. Canada"},{"key":"29_CR28","unstructured":"Scipy: numpy.append numpy v1.20 manual (2020). https:\/\/docs.scipy.org\/doc\/numpy\/reference\/genrated\/numpy.append.html"},{"key":"29_CR29","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. Proc. Comput. Sci. 171, 1381\u20131388 (2020)","journal-title":"Proc. Comput. Sci."},{"key":"29_CR30","unstructured":"sklearn: sklearn.model$$\\_$$selection.train$$\\_$$test]$$\\_$$split scikit-learn 0.24.1 documentationdocumentation (www document) (2020). https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.model_selection.train_test_split.html"},{"key":"29_CR31","unstructured":"Speaks, A.: Audrey: the first speech recognition system, October 2014. https:\/\/astaspeaks.wordpress.com\/2014\/10\/13\/audrey-the-first-speech-recognition-system\/\/"},{"key":"29_CR32","doi-asserted-by":"publisher","unstructured":"Sultana, S., Rahman, M.S., Iqbal, M.Z.: Recent advancement in speech recognition for bangla: a survey. Int. J. Adv. Comput. Sci. Appl. 12(3) (2021). https:\/\/doi.org\/10.14569\/IJACSA.2021.0120365http:\/\/dx.doi.org\/10.14569\/IJACSA.2021.0120365","DOI":"10.14569\/IJACSA.2021.0120365"},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Taufika, D., Hanafiaha, N.: Autovat: An automated visual acuity test using spoken digit recognition with MEL frequency cepstral coefficients and convolutional neural network. In: 5th International Conference on Computer Science and Computational Intelligence 2020. vol. 179, pp. 458\u2013467 (2021)","DOI":"10.1016\/j.procs.2021.01.029"},{"key":"29_CR34","unstructured":"tensorflow: tensorflow.org\/guide\/keras\/sequential$$\\_$$tensorflow core v2.4.1] (www document) (2020). https:\/\/www.tensorflow.org\/guide\/keras\/sequential_model"},{"key":"29_CR35","unstructured":"Watt, S., Kostylev, M.: Spoken digit classification using spin-wave delay-line active-ring reservoir computing. arXiv (2020)"},{"key":"29_CR36","unstructured":"Wikiland: List of languages by total number of speakers (2019). https:\/\/wikiwand.com\/en\/List_of_languages_by_number_of_native_speakers\/\/"},{"issue":"1","key":"29_CR37","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1515\/comp-2019-0004","volume":"9","author":"N Zerari","year":"2019","unstructured":"Zerari, N., Samir, A., Hassen, B., Raymond, C.: Bidirectional deep architecture for Arabic speech recognition speech recognition using multiscale scattering of audio signals and long short-term memory of neural networks. Open Comput. Sci. 9(1), 92\u2013102 (2019)","journal-title":"Open Comput. Sci."},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, W., Lei, W., Xu, X., Xing, X.: Improved music genre classification with convolutional neural networks. In: INTERSPEECH (2016)","DOI":"10.21437\/Interspeech.2016-1236"}],"updated-by":[{"DOI":"10.1007\/978-3-030-82269-9_31","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T00:00:00Z","timestamp":1627257600000}}],"container-title":["Communications in Computer and Information Science","Applied Intelligence and Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-82269-9_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T09:27:56Z","timestamp":1635154076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-82269-9_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030822682","9783030822699"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-82269-9_29","relation":{"correction":[{"id-type":"doi","id":"10.1007\/978-3-030-82269-9_31","asserted-by":"object"}]},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"26 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"26 July 2021","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The caption of figure 9 in the original version of chapter 29 contained erroneous data and typographical errors. The wrong value and typographical errors have been corrected.","order":4,"name":"change_details","label":"Change Details","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applied Intelligence and Informatics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nottingham","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 July 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apii2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aii2021.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Proconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"107","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":"26","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":"4","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":"24% - 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":"3","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":"5","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the COVID-19 pandemic the conference was held in a fully virtual mode.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}