{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:32:17Z","timestamp":1767339137786,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031346187"},{"type":"electronic","value":"9783031346194"}],"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_42","type":"book-chapter","created":{"date-parts":[[2023,6,10]],"date-time":"2023-06-10T19:01:31Z","timestamp":1686423691000},"page":"539-550","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Bangla Speech Emotion Recognition Using 3D CNN Bi-LSTM Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7879-7246","authenticated-orcid":false,"given":"Md. Riadul","family":"Islam","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5465-8519","authenticated-orcid":false,"given":"M. A. H.","family":"Akhand","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3150-0510","authenticated-orcid":false,"given":"Md Abdus Samad","family":"Kamal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,11]]},"reference":[{"key":"42_CR1","doi-asserted-by":"publisher","unstructured":"Atila, O., \u015eeng\u00fcr, A.: Attention guided 3D CNN-LSTM model for accurate speech based emotion recognition. Appl. Acoust. 182 (2021). https:\/\/doi.org\/10.1016\/j.apacoust.2021.108260","DOI":"10.1016\/j.apacoust.2021.108260"},{"key":"42_CR2","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.specom.2020.12.009","volume":"127","author":"S Zhang","year":"2021","unstructured":"Zhang, S., Tao, X., Chuang, Y., Zhao, X.: Learning deep multimodal affective features for spontaneous speech emotion recognition. Speech Commun. 127, 73\u201381 (2021). https:\/\/doi.org\/10.1016\/j.specom.2020.12.009","journal-title":"Speech Commun."},{"key":"42_CR3","doi-asserted-by":"publisher","unstructured":"Anvarjon, T., Mustaqeem, Kwon, S.: Deep-net: a lightweight CNN-based speech emotion recognition system using deep frequency features. Sensors. 20, 5212 (2020). https:\/\/doi.org\/10.3390\/s20185212","DOI":"10.3390\/s20185212"},{"key":"42_CR4","doi-asserted-by":"publisher","unstructured":"Mustaqeem, Kwon, S.: CLSTM: deep feature-based speech emotion recognition using the hierarchical ConvLSTM network. Mathematics. 8, 2133 (2020). https:\/\/doi.org\/10.3390\/math8122133","DOI":"10.3390\/math8122133"},{"key":"42_CR5","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","volume":"47","author":"J Zhao","year":"2019","unstructured":"Zhao, J., Mao, X., Chen, L.: Speech emotion recognition using deep 1D & 2D CNN LSTM networks. Biomed. Signal Process. Control. 47, 312\u2013323 (2019). https:\/\/doi.org\/10.1016\/j.bspc.2018.08.035","journal-title":"Biomed. Signal Process. Control."},{"key":"42_CR6","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1109\/JSTSP.2017.2764438","volume":"11","author":"G Trigeorgis","year":"2017","unstructured":"Trigeorgis, G., Nicolaou, M.A., Schuller, W.: End-to-end multimodal emotion recognition. IEEE J. Sel. Top. Signal Process. 11, 1301\u20131309 (2017)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"42_CR7","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1109\/LSP.2021.3055755","volume":"28","author":"C Guanghui","year":"2021","unstructured":"Guanghui, C., Xiaoping, Z.: Multi-modal emotion recognition by fusing correlation features of speech-visual. IEEE Signal Process. Lett. 28, 533\u2013537 (2021). https:\/\/doi.org\/10.1109\/LSP.2021.3055755","journal-title":"IEEE Signal Process. Lett."},{"issue":"1","key":"42_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-021-00208-5","volume":"2021","author":"D Tang","year":"2021","unstructured":"Tang, D., Kuppens, P., Geurts, L., van Waterschoot, T.: End-to-end speech emotion recognition using a novel context-stacking dilated convolution neural network. EURASIP J. Audio Speech Music Process. 2021(1), 1\u201316 (2021). https:\/\/doi.org\/10.1186\/s13636-021-00208-5","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"42_CR9","doi-asserted-by":"publisher","unstructured":"Zhang, H., Gou, R., Shang, J., Shen, F., Wu, Y., Dai, G.: Pre-trained deep convolution neural network model with attention for speech emotion recognition. Front. Physiol. 12 (2021). https:\/\/doi.org\/10.3389\/fphys.2021.643202","DOI":"10.3389\/fphys.2021.643202"},{"issue":"3","key":"42_CR10","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1007\/s00500-020-05501-7","volume":"25","author":"E Mansouri-Benssassi","year":"2021","unstructured":"Mansouri-Benssassi, E., Ye, J.: Generalisation and robustness investigation for facial and speech emotion recognition using bio-inspired spiking neural networks. Soft. Comput. 25(3), 1717\u20131730 (2021). https:\/\/doi.org\/10.1007\/s00500-020-05501-7","journal-title":"Soft. Comput."},{"key":"42_CR11","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.neunet.2021.03.013","volume":"141","author":"Z Zhao","year":"2021","unstructured":"Zhao, Z., et al.: Combining a parallel 2D CNN with a self-attention dilated residual network for CTC-based discrete speech emotion recognition. Neural Netw. 141, 52\u201360 (2021). https:\/\/doi.org\/10.1016\/j.neunet.2021.03.013","journal-title":"Neural Netw."},{"key":"42_CR12","doi-asserted-by":"publisher","first-page":"2362","DOI":"10.3390\/electronics11152362","volume":"11","author":"MR Islam","year":"2022","unstructured":"Islam, M.R., Akhand, M.A.H., Kamal, M.A.S., Yamada, K.: Recognition of emotion with intensity from speech signal using 3D transformed feature and deep learning. Electronics 11, 2362 (2022). https:\/\/doi.org\/10.3390\/electronics11152362","journal-title":"Electronics"},{"key":"42_CR13","doi-asserted-by":"publisher","first-page":"44317","DOI":"10.1109\/ACCESS.2019.2908285","volume":"7","author":"JX Chen","year":"2019","unstructured":"Chen, J.X., Zhang, P.W., Mao, Z.J., Huang, Y.F., Jiang, D.M., Zhang, Y.N.: Accurate EEG-based emotion recognition on combined features using deep convolutional neural networks. IEEE Access. 7, 44317\u201344328 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2908285","journal-title":"IEEE Access."},{"key":"42_CR14","doi-asserted-by":"publisher","unstructured":"Mustaqeem, Kwon, S.: A CNN-assisted enhanced audio signal processing for speech emotion recognition. Sens. (Switz.) 20 (2020). https:\/\/doi.org\/10.3390\/s20010183","DOI":"10.3390\/s20010183"},{"key":"42_CR15","doi-asserted-by":"publisher","unstructured":"Livingstone, S., Russo, F.: The ryerson audio-visual database of emotional speech and song (RAVDESS). PLoS One 13 (2018). https:\/\/doi.org\/10.5281\/zenodo.1188976","DOI":"10.5281\/zenodo.1188976"},{"key":"42_CR16","doi-asserted-by":"publisher","unstructured":"Mustaqeem, Sajjad, M., Kwon, S.: Clustering-based speech emotion recognition by incorporating learned features and deep BiLSTM. IEEE Access. 8, 79861\u201379875 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2990405","DOI":"10.1109\/ACCESS.2020.2990405"},{"key":"42_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0250173","volume":"16","author":"S Sultana","year":"2021","unstructured":"Sultana, S., Rahman, M.S., Selim, M.R., Iqbal, M.Z.: SUST Bangla emotional speech corpus (SUBESCO): an audio-only emotional speech corpus for Bangla. PLoS One 16, 1\u201327 (2021). https:\/\/doi.org\/10.1371\/journal.pone.0250173","journal-title":"PLoS One"},{"key":"42_CR18","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1109\/ACCESS.2021.3136251","volume":"10","author":"S Sultana","year":"2022","unstructured":"Sultana, S., Iqbal, M.Z., Selim, M.R., Rashid, M.M., Rahman, M.S.: Bangla speech emotion recognition and cross-lingual study using deep CNN and BLSTM networks. IEEE Access 10, 564\u2013578 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2021.3136251","journal-title":"IEEE Access"},{"key":"42_CR19","doi-asserted-by":"publisher","unstructured":"Hajarolasvadi, N., Demirel, H.: 3D CNN-based speech emotion recognition using k-means clustering and spectrograms. Entropy. 21 (2019). https:\/\/doi.org\/10.3390\/e21050479","DOI":"10.3390\/e21050479"},{"key":"42_CR20","doi-asserted-by":"publisher","unstructured":"Al Mamun, S.K., Hassan, M.M., Islam, M.R., Raihan, M.: Obstructive sleep apnea detection based on sound interval frequency using wearable device. In: 2020 11th International Conference on Computer Communication Network and Technology, ICCCNT 2020, pp. 6\u20139 (2020). https:\/\/doi.org\/10.1109\/ICCCNT49239.2020.9225450","DOI":"10.1109\/ICCCNT49239.2020.9225450"},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Islam, M.R., Hassan, M.M., Raihan, M., Datto, S.K., Shahriar, A., More, A.: A wireless electronic stethoscope to classify children heart sound abnormalities (2019)","DOI":"10.1109\/ICCIT48885.2019.9038406"},{"key":"42_CR22","doi-asserted-by":"publisher","unstructured":"Garrido, M.: The feedforward short-time Fourier transform. IEEE Trans. Circuits Syst. II Express Briefs. 63, 868\u2013872 (2016). https:\/\/doi.org\/10.1109\/TCSII.2016.2534838","DOI":"10.1109\/TCSII.2016.2534838"},{"key":"42_CR23","unstructured":"M\u00fcller, M., Balke, S.: Short-time Fourier transform and chroma features. 10 (2015)"},{"key":"42_CR24","doi-asserted-by":"publisher","first-page":"125868","DOI":"10.1109\/ACCESS.2019.2938007","volume":"7","author":"H Meng","year":"2019","unstructured":"Meng, H., Yan, T., Yuan, F., Wei, H.: Speech Emotion recognition from 3D log-mel spectrograms with deep learning network. IEEE Access 7, 125868\u2013125881 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2938007","journal-title":"IEEE Access"},{"key":"42_CR25","doi-asserted-by":"publisher","unstructured":"Angadi, S., Reddy, V.S.: Hybrid deep network scheme for emotion recognition in speech. Int. J. Intell. Eng. Syst. 12, 59\u201367 (2019). https:\/\/doi.org\/10.22266\/IJIES2019.0630.07","DOI":"10.22266\/IJIES2019.0630.07"},{"key":"42_CR26","doi-asserted-by":"publisher","first-page":"110212","DOI":"10.1016\/j.chaos.2020.110212","volume":"140","author":"F Shahid","year":"2020","unstructured":"Shahid, F., Zameer, A., Muneeb, M.: Predictions for COVID-19 with deep learning models of LSTM. GRU and Bi-LSTM. Chaos Solitons Fractals 140, 110212 (2020). https:\/\/doi.org\/10.1016\/j.chaos.2020.110212","journal-title":"GRU and Bi-LSTM. Chaos Solitons Fractals"}],"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_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,10]],"date-time":"2023-06-10T19:09:32Z","timestamp":1686424172000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-34619-4_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031346187","9783031346194"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-34619-4_42","relation":{},"ISSN":["1867-8211","1867-822X"],"issn-type":[{"type":"print","value":"1867-8211"},{"type":"electronic","value":"1867-822X"}],"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)"}}]}}