{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:23:25Z","timestamp":1783556605871,"version":"3.55.0"},"reference-count":32,"publisher":"Informa UK Limited","issue":"1","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076092"],"award-info":[{"award-number":["62076092"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Connection Science"],"published-print":{"date-parts":[[2024,12,31]]},"DOI":"10.1080\/09540091.2024.2312103","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T18:26:28Z","timestamp":1706811988000},"update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":10,"title":["Knowledge enhancement for speech emotion recognition via multi-level acoustic feature"],"prefix":"10.1080","volume":"36","author":[{"given":"Huan","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nianxin","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haijiao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,2]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"crossref","unstructured":"Badshah A. M. Ahmad J. Rahim N. & Baik S. W. (2017). Speech emotion recognition from spectrograms with deep convolutional neural network. In International conference on platform technology and service (PlatCon) (pp. 1\u20135).","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"e_1_3_2_3_1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski A.","year":"2020","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., & Auli, M. (2020). wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems, 33, 12449\u201312460.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_4_1","unstructured":"Bakhshi A. Wong A. S. W. & Chalup S. K. (2020). End-to-end speech emotion recognition based on time and frequency information using deep neural networks. In Proceedings of the 24th European conference on artificial intelligence (ECAI) (pp. 969\u2013975)."},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"e_1_3_2_6_1","doi-asserted-by":"crossref","unstructured":"Cai X. Yuan J. Zheng R. Huang L. & Church K. (2021). Speech emotion recognition with multi-task learning. In Proceedings of the 22nd annual conference of the international speech communication association (Interspeech) (pp. 4508\u20134512).","DOI":"10.21437\/Interspeech.2021-1852"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.03.209"},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2023.2283390"},{"key":"e_1_3_2_9_1","unstructured":"Chen L. & Rudnicky A. I. (2021). Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition. CoRR abs\/2110.06309."},{"key":"e_1_3_2_10_1","doi-asserted-by":"crossref","unstructured":"Cummins N. Amiriparian S. Hagerer G. Batliner A. Steidl S. & Schuller B. W. (2017). An image-based deep spectrum feature representation for the recognition of emotional speech. In Proceedings of the 25th ACM international conference on multimedia (pp. 478\u2013484).","DOI":"10.1145\/3123266.3123371"},{"key":"e_1_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Guo L. Wang L. Xu C. Dang J. Chng E. S. & Li H. (2021). Representation learning with spectro-temporal-channel attention for speech emotion recognition. In IEEE international conference on acoustics speech and signal processing (ICASSP) (pp. 6304\u20136308).","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2928297"},{"key":"e_1_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Kim T. Cho S. Choi S. Park S. & Lee S. (2020). Emotional voice conversion using multitask learning with text-to-speech. In IEEE international conference on acoustics speech and signal processing (ICASSP) (pp. 7774\u20137778).","DOI":"10.1109\/ICASSP40776.2020.9053255"},{"key":"e_1_3_2_14_1","doi-asserted-by":"crossref","unstructured":"Kumbhar H. S. & Bhandari S. U. (2019). Speech emotion recognition using MFCC features and LSTM network. In Proceedings of the 5th international conference on computing communication control and automation (ICCUBEA) (pp. 1\u20133).","DOI":"10.1109\/ICCUBEA47591.2019.9129067"},{"key":"e_1_3_2_15_1","doi-asserted-by":"crossref","unstructured":"Latif S. Rana R. Khalifa S. Jurdak R. & Epps J. (2019). Direct modelling of speech emotion from raw speech. In Proceedings of the 20th annual conference of the international speech communication association (Interspeech) (pp. 3920\u20133924).","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40305-019-00280-x"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2023.2189217"},{"key":"e_1_3_2_18_1","doi-asserted-by":"crossref","unstructured":"McFee B. Raffel C. Liang D. Ellis D. P. W. McVicar M. Battenberg E. & Nieto O. (2015). librosa: Audio and music signal analysis in python. In Proceedings of the 14th python in science conference (SciPy) (pp. 18\u201324).","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9172-2"},{"key":"e_1_3_2_20_1","unstructured":"Ren Z. Kong Q. Qian K. Plumbley M. D. & Schuller B. W. (2018). Attention-based convolutional neural networks for acoustic scene classification. In Proceedings of the workshop on detection and classification of acoustic scenes and events (DCASE) (pp. 39\u201343)."},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2015.1080224"},{"key":"e_1_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Tarantino L. Garner P. N. & Lazaridis A. (2019). Self-attention for speech emotion recognition. In Proceedings of the 20th annual conference of the international speech communication association (Interspeech) (pp. 2578\u20132582).","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"e_1_3_2_23_1","doi-asserted-by":"crossref","unstructured":"Tsai Y. H. Bai S. Liang P. P. Kolter J. Z. Morency L. & Salakhutdinov R. (2019). Multimodal transformer for unaligned multimodal language sequences. In Proceedings of the 57th conference of the association for computational linguistics (ACL) (pp. 6558\u20136569).","DOI":"10.18653\/v1\/P19-1656"},{"key":"e_1_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Wani T. M. Gunawan T. S. Qadri S. A. A. Mansor H. Kartiwi M. & Ismail N. (2020). Speech emotion recognition using convolution neural networks and deep stride convolutional neural networks. In Proceedings of the 6th international conference on wireless and telematics (ICWT) (pp. 1\u20136).","DOI":"10.1109\/ICWT50448.2020.9243622"},{"key":"e_1_3_2_25_1","doi-asserted-by":"crossref","unstructured":"Wu W. Zhang C. & Woodland P. C. (2021). Emotion recognition by fusing time synchronous and time asynchronous representations. In IEEE international conference on acoustics speech and signal processing (ICASSP) (pp. 6269\u20136273).","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2023.2289833"},{"key":"e_1_3_2_27_1","unstructured":"Zadeh A. Liang P. P. Poria S. Cambria E. & Morency L. (2018). Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph. In Proceedings of the 56th annual meeting of the association for computational linguistics (ACL) (pp. 2236\u20132246)."},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"e_1_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2947464"},{"key":"e_1_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Zhao H. Chen H. Xiao Y. & Zhang Z. (2023). Privacy-enhanced federated learning against attribute inference attack for speech emotion recognition. In IEEE international conference on acoustics speech and signal processing (ICASSP) (pp. 1\u20135).","DOI":"10.1109\/ICASSP49357.2023.10095737"},{"key":"e_1_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/Access.6287639"},{"key":"e_1_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02943243"},{"key":"e_1_3_2_33_1","doi-asserted-by":"crossref","unstructured":"Zou H. Si Y. Chen C. Rajan D. & Chng E. S. (2022). Speech emotion recognition with co-attention based multi-level acoustic information. In IEEE international conference on acoustics speech and signal processing (ICASSP) (pp. 7367\u20137371).","DOI":"10.1109\/ICASSP43922.2022.9747095"}],"container-title":["Connection Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/09540091.2024.2312103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T15:01:27Z","timestamp":1734447687000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/09540091.2024.2312103"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,12,31]]}},"alternative-id":["10.1080\/09540091.2024.2312103"],"URL":"https:\/\/doi.org\/10.1080\/09540091.2024.2312103","relation":{},"ISSN":["0954-0091","1360-0494"],"issn-type":[{"value":"0954-0091","type":"print"},{"value":"1360-0494","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=ccos20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=ccos20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2023-10-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2312103"}}