{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:08:36Z","timestamp":1776107316476,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,17]]},"DOI":"10.1145\/3723178.3723262","type":"proceedings-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T07:20:33Z","timestamp":1749194433000},"page":"637-644","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Bangla Speech Emotion Recognition Based on Audio Features Using CNN and LSTM"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3792-0801","authenticated-orcid":false,"given":"Plabon","family":"Talukder","sequence":"first","affiliation":[{"name":"Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh and Computer Science & Engineering, Metropolitan University, Sylhet, Sylhet, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7014-3205","authenticated-orcid":false,"given":"Md. Faysal","family":"Ahamed","sequence":"additional","affiliation":[{"name":"Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1989-4385","authenticated-orcid":false,"given":"Md. Rabiul","family":"Islam","sequence":"additional","affiliation":[{"name":"Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh"}]}],"member":"320","published-online":{"date-parts":[[2025,6,6]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Caroline Etienne Guillaume Fidanza Andrei Petrovskii Laurence Devillers and Benoit Schmauch. 2018. Speech Emotion Recognition with Data Augmentation and Layer-wise Learning Rate Adjustment. (02 2018).","DOI":"10.21437\/SMM.2018-5"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-34619-4_42"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Jahangir Teh Wah Ghulam Mujtaba Roobaea Alroobaea Zahid Shaikh and Ali Ihsan. 2022. Convolutional neural network-based cross-corpus speech emotion recognition with data augmentation and features fusion. Machine Vision and Applications 33 (05 2022). 10.1007\/s00138-022-01294-x","DOI":"10.1007\/s00138-022-01294-x"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"P. Kathirvel M. Manikandan S. Senthilkumar and Soman Kp. 2011. Noise robust zerocrossing rate computation for audio signal classification. TISC 2011 - Proceedings of the 3rd International Conference on Trendz in Information Sciences and Computing (12 2011). 10.1109\/TISC.2011.6169086","DOI":"10.1109\/TISC.2011.6169086"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Mustaqeem Khan and Soonil Kwon. 2020. CLSTM: Deep Feature-Based Speech Emotion Recognition Using the Hierarchical ConvLSTM Network. 8 (12 2020) 19mathema. 10.3390\/math8122133","DOI":"10.3390\/math8122133"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Hao Meng Tianhao Yan Fei Yuan and Hongwei Wei. 2019. Speech Emotion Recognition From 3D Log-Mel Spectrograms With Deep Learning Network. IEEE Access (08 2019) 1\u20131. 10.1109\/ACCESS.2019.2938007","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Zhichao Peng Xingfeng Li Zhi Zhu Masashi Unoki Jianwu Dang and Masato Akagi. 2020. Speech Emotion Recognition Using 3D Convolutions and Attention-Based Sliding Recurrent Networks With Auditory Front-Ends. IEEE Access PP (01 2020) 1\u20131. 10.1109\/ACCESS.2020.2967791","DOI":"10.1109\/ACCESS.2020.2967791"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Md Rahman Debopriya Roy and Md Hasan. 2018. Dynamic Time Warping Assisted SVM Classifier for Bangla Speech Recognition. 1\u20136. 10.1109\/IC4ME2.2018.8465640","DOI":"10.1109\/IC4ME2.2018.8465640"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Aharon Satt Shai Rozenberg and Ron Hoory. 2017. Efficient Emotion Recognition from Speech Using Deep Learning on Spectrograms. 1089\u20131093. 10.21437\/Interspeech.2017-200","DOI":"10.21437\/Interspeech.2017-200"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Sadia Sultana M\u00a0Zafar Iqbal M\u00a0Reza Selim Md\u00a0Mijanur Rashid and M\u00a0Shahidur Rahman. 2022. Bangla speech emotion recognition and cross-lingual study using deep CNN and BLSTM networks. IEEE Access 10 (2022) 564\u2013578.","DOI":"10.1109\/ACCESS.2021.3136251"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Sadia Sultana M\u00a0Shahidur Rahman M\u00a0Reza Selim and M\u00a0Zafar Iqbal. 2021. SUST Bangla Emotional Speech Corpus (SUBESCO): An audio-only emotional speech corpus for Bangla. PLoS One 16 4 (April 2021) e0250173.","DOI":"10.1371\/journal.pone.0250173"},{"key":"e_1_3_3_1_14_2","unstructured":"Muhammad Turab Teerath Kumar Malika Bendechache and Takfarinas Saber. 2022. Investigating Multi-feature selection and ensembling for audio classification. (June 2022). arxiv:cs.SD\/2206.07511"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Jianfeng Zhao Xia Mao and Lijiang Chen. 2019. Speech emotion recognition using deep 1D & 2D CNN LSTM networks. Biomedical Signal Processing and Control 47 (01 2019) 312\u2013323. 10.1016\/j.bspc.2018.08.035","DOI":"10.1016\/j.bspc.2018.08.035"}],"event":{"name":"ICCA 2024: 3rd International Conference on Computing Advancements","location":"Dhaka Bangladesh","acronym":"ICCA 2024"},"container-title":["Proceedings of the 3rd International Conference on Computing Advancements"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723178.3723262","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3723178.3723262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:56:47Z","timestamp":1750298207000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723178.3723262"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":14,"alternative-id":["10.1145\/3723178.3723262","10.1145\/3723178"],"URL":"https:\/\/doi.org\/10.1145\/3723178.3723262","relation":{},"subject":[],"published":{"date-parts":[[2024,10,17]]},"assertion":[{"value":"2025-06-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}