{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T23:10:07Z","timestamp":1785193807487,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"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":[[2024,11,8]]},"DOI":"10.1145\/3705927.3705939","type":"proceedings-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T12:00:58Z","timestamp":1737547258000},"page":"67-71","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Time-Distributed CNN-LSTM with Attention Model for Speech Based Emotion Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4643-8708","authenticated-orcid":false,"given":"Kedar","family":"Deshpande","sequence":"first","affiliation":[{"name":"IIIT Bangalore, Bengaluru, India,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8352-472X","authenticated-orcid":false,"given":"Manjit Singh","family":"Sodhi","sequence":"additional","affiliation":[{"name":"IBM Bangalore, Bengaluru, India,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7538-895X","authenticated-orcid":false,"given":"Nidhi","family":"Raniyer","sequence":"additional","affiliation":[{"name":"IBM Bangalore, Bengaluru, India,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2278-9148","authenticated-orcid":false,"given":"Madhav","family":"Rao","sequence":"additional","affiliation":[{"name":"IIIT Bangalore, Bengaluru, India,"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,1,22]]},"reference":[{"key":"e_1_3_3_1_1_2","unstructured":"https:\/\/github.com\/mlcoder7\/emotion-recognition"},{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108260"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2772340"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11233935"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.104886"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-022-01633-9"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3279689"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1093\/iwc\/iwac042"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3304544"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3275565"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3055755"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3375351"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076364"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3372581"},{"key":"e_1_3_3_1_15_2","first-page":"101894","volume":"59","author":"Issa D.","year":"2020","unstructured":"Issa, D., Demirci, M.F., Yazici, A.: Speech emotion recognition with deep convolutional neural networks. Biomedical Signal Processing and Control 59, 101894 (2020)","journal-title":"Control"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3020506"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3048737"},{"key":"e_1_3_3_1_19_2","volume-title":"Russo","author":"Livingstone S.R.","year":"1963","unstructured":"Livingstone, S.R., Russo, F.A.: The ryerson audio-visual database of emotional speech and song (ravdess): A dynamic, multimodal set of facial and vocal expressions in north american english. PloS one 13(5), e0196391 (2018)"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21227665"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2981418"},{"key":"e_1_3_3_1_22_2","volume-title":"Alqahtani","author":"Ong K.L.","year":"2023","unstructured":"Ong, K.L., Lee, C.P., Lim, H.S., Lim, K.M., Alqahtani, A.: Mel-mvitv2: Enhanced speech emotion recognition with mel spectrogram and improved multiscale vision transformers. IEEE Access (2023)"},{"key":"e_1_3_3_1_23_2","volume-title":"Ferrer","author":"Pepino L.","year":"2021","unstructured":"Pepino, L., Riera, P., Ferrer, L.: Emotion recognition from speech using wav2vec2.0 embeddings. arXiv preprint arXiv:2104.03502 (2021)"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2022.3142112"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446974"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107316"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3276628"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3132233"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3069818"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3233324"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3363444"}],"event":{"name":"DMIP '24: 2024 7th International Conference on Digital Medicine and Image Processing","location":"Osaka Japan","acronym":"DMIP '24"},"container-title":["Proceedings of the 2024 7th International Conference on Digital Medicine and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3705927.3705939","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3705927.3705939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:13Z","timestamp":1750295893000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3705927.3705939"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,8]]},"references-count":31,"alternative-id":["10.1145\/3705927.3705939","10.1145\/3705927"],"URL":"https:\/\/doi.org\/10.1145\/3705927.3705939","relation":{},"subject":[],"published":{"date-parts":[[2024,11,8]]},"assertion":[{"value":"2025-01-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}