{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:45:49Z","timestamp":1782992749490,"version":"3.54.5"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T00:00:00Z","timestamp":1720483200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T00:00:00Z","timestamp":1720483200000},"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":["J Supercomput"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1007\/s11227-024-06158-x","type":"journal-article","created":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T15:22:41Z","timestamp":1720538561000},"page":"23667-23688","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Exploring the potential of Wav2vec 2.0 for speech emotion recognition using classifier combination and attention-based feature fusion"],"prefix":"10.1007","volume":"80","author":[{"given":"Babak","family":"Nasersharif","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Namvarpour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,9]]},"reference":[{"issue":"1","key":"6158_CR1","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie R, Douglas-Cowie E, Tsapatsoulis N, Votsis G, Kollias S, Fellenz W, Taylor J (2001) Emotion recognition in human-computer interaction. IEEE Signal Process Mag 18(1):32\u201380. https:\/\/doi.org\/10.1109\/79.911197","journal-title":"IEEE Signal Process Mag"},{"issue":"2\u20133","key":"6158_CR2","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1080\/87565648909540433","volume":"5","author":"D Van Lancker","year":"1989","unstructured":"Van Lancker D, Cornelius C, Kreiman J (1989) Recognition of emotional-prosodic meanings in speech by autistic, schizophrenic, and normal children. Dev Neuropsychol 5(2\u20133):207\u2013226. https:\/\/doi.org\/10.1080\/87565648909540433","journal-title":"Dev Neuropsychol"},{"key":"6158_CR3","unstructured":"Florianne P, Boco O, Karen D, Tercias KC, Raquel C, Cristina R, Guevara L, Naval P (2010) EMSys: an emotion monitoring system for call center agents"},{"issue":"4","key":"6158_CR4","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso C, Bulut M, Lee C-C, Kazemzadeh A, Mower E, Kim S, Chang JN, Lee S, Narayanan SS (2008) IEMOCAP: interactive emotional dyadic motion capture database. Lang Resour Eval 42(4):335\u2013359. https:\/\/doi.org\/10.1007\/s10579-008-9076-6","journal-title":"Lang Resour Eval"},{"key":"6158_CR5","doi-asserted-by":"publisher","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier W, Weiss B (2005) A database of German emotional speech. In: 9th European Conference on Speech Communication and Technology, vol 5, pp 1517\u20131520. https:\/\/doi.org\/10.21437\/Interspeech.2005-446","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"5","key":"6158_CR6","doi-asserted-by":"publisher","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone SR, Russo FA (2018) 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. https:\/\/doi.org\/10.1371\/journal.pone.0196391","journal-title":"PLoS ONE"},{"key":"6158_CR7","unstructured":"Nezami OM, Lou PJ, Karami M (2019) ShEMO\u2013a large-scale validated database for Persian speech emotion detection. arXiv:1906.01155"},{"issue":"4","key":"6158_CR8","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1109\/TAFFC.2017.2736999","volume":"10","author":"R Lotfian","year":"2019","unstructured":"Lotfian R, Busso C (2019) Building naturalistic emotionally balanced speech corpus by retrieving emotional speech from existing podcast recordings. IEEE Trans Affect Comput 10(4):471\u2013483. https:\/\/doi.org\/10.1109\/TAFFC.2017.2736999","journal-title":"IEEE Trans Affect Comput"},{"key":"6158_CR9","doi-asserted-by":"publisher","unstructured":"Mohamed A, Lee H-y, Borgholt L, Havtorn JD, Edin J, Igel C, Kirchhoff K, Li S-W, Livescu K, Maal\u00f8e L, Sainath TN, Watanabe S (2022) Self-Supervised Speech Representation Learning: a Review. IEEE J Selected Topics Signal Process. https:\/\/doi.org\/10.48550\/arXiv.2205.10643","DOI":"10.48550\/arXiv.2205.10643"},{"key":"6158_CR10","doi-asserted-by":"publisher","unstructured":"Chung Y-A, Glass J (2020) Generative pre-training for speech with autoregressive predictive coding. In: 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). arXiv:1910.12607, https:\/\/doi.org\/10.48550\/arXiv.1910.12607","DOI":"10.48550\/arXiv.1910.12607"},{"key":"6158_CR11","doi-asserted-by":"publisher","unstructured":"Schneider S, Baevski A, Collobert R, Auli M (2019) Wav2vec: unsupervised pre-training for speech recognition. arXiv:1904.05862, https:\/\/doi.org\/10.48550\/arXiv.1904.05862","DOI":"10.48550\/arXiv.1904.05862"},{"key":"6158_CR12","doi-asserted-by":"publisher","unstructured":"Liu AT, Yang S-w, Chi P-H, Hsu P-c, Lee H-y (2020) Mockingjay: unsupervised speech representation learning with deep bidirectional transformer encoders. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 6419\u20136423. arXiv:1910.12638, https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054458","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"6158_CR13","unstructured":"Baevski A, Zhou Y, Mohamed A, et\u00a0al. (2020) Wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in neural information processing systems, vol\u00a033, Curran Associates, Inc., pp 12449\u201312460"},{"key":"6158_CR14","doi-asserted-by":"publisher","unstructured":"Hsu W-N, Bolte B, Tsai Y-HH, Lakhotia K, Salakhutdinov R, Mohamed A (2021) HuBERT: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Tran Audio, Speech, Lang Process. https:\/\/doi.org\/10.48550\/arXiv.2106.07447","DOI":"10.48550\/arXiv.2106.07447"},{"issue":"6","key":"6158_CR15","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen S, Wang C, Chen Z, Wu Y, Liu S, Chen Z, Li J, Kanda N, Yoshioka T, Xiao X, Wu J, Zhou L, Ren S, Qian Y, Qian Y, Wu J, Zeng M, Yu X, Wei F (2022) WavLM: large-scale self-supervised pre-training for full stack speech processing. IEEE J Selected Topics Signal Process 16(6):1505\u20131518. https:\/\/doi.org\/10.1109\/JSTSP.2022.3188113","journal-title":"IEEE J Selected Topics Signal Process"},{"key":"6158_CR16","doi-asserted-by":"publisher","unstructured":"Morais E, Hoory R, Zhu W, et\u00a0al. (2022) Speech emotion recognition using self-supervised features. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 6922\u20136926. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747870","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"6158_CR17","doi-asserted-by":"crossref","unstructured":"Pepino L, Riera P, Ferrer L (2021) Emotion recognition from speech using Wav2vec 2.0 embeddings. arXiv:2104.03502","DOI":"10.21437\/Interspeech.2021-703"},{"key":"6158_CR18","doi-asserted-by":"publisher","unstructured":"Xia Y, Chen L-W, Rudnicky A, Stern RM (2021) Temporal context in speech emotion recognition. In: Interspeech 2021, ISCA, pp 3370\u20133374. https:\/\/doi.org\/10.21437\/Interspeech.2021-1840","DOI":"10.21437\/Interspeech.2021-1840"},{"issue":"12","key":"6158_CR19","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1145\/3381831","volume":"63","author":"R Schwartz","year":"2020","unstructured":"Schwartz R, Dodge J, Smith NA, Etzioni O (2020) Green AI. Commun ACM 63(12):54\u201363. https:\/\/doi.org\/10.1145\/3381831","journal-title":"Commun ACM"},{"key":"6158_CR20","doi-asserted-by":"publisher","unstructured":"Zhuang F, Qi Z, Duan K, Xi D, Zhu Y, Zhu H, Xiong H, He Q (2019) A comprehensive survey on transfer learning. https:\/\/doi.org\/10.48550\/ARXIV.1911.02685","DOI":"10.48550\/ARXIV.1911.02685"},{"key":"6158_CR21","unstructured":"Chen L-W, Rudnicky A (2021) Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition. arXiv:2110.06309"},{"key":"6158_CR22","doi-asserted-by":"crossref","unstructured":"Sharma M (2022) Multi-lingual multi-task speech emotion recognition using wav2vec 2.0. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 6907\u20136911","DOI":"10.1109\/ICASSP43922.2022.9747417"},{"key":"6158_CR23","doi-asserted-by":"crossref","unstructured":"Li Y, Bell P, Lai C (2021) Fusing ASR outputs in joint training for speech emotion recognition. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 7362\u20137366","DOI":"10.1109\/ICASSP43922.2022.9746289"},{"issue":"3","key":"6158_CR24","doi-asserted-by":"publisher","first-page":"79","DOI":"10.3390\/bdcc6030079","volume":"6","author":"K Wongpatikaseree","year":"2022","unstructured":"Wongpatikaseree K, Singkul S, Hnoohom N, Yuenyong S (2022) Real-time end-to-end speech emotion recognition with cross-domain adaptation. Big Data Cogn Comput 6(3):79. https:\/\/doi.org\/10.3390\/bdcc6030079","journal-title":"Big Data Cogn Comput"},{"key":"6158_CR25","unstructured":"Srivastava H, Ghosh S, Umesh S (2022) MMER: multimodal multi-task learning for emotion recognition in spoken utterances. arXiv:2203.16794"},{"key":"6158_CR26","doi-asserted-by":"publisher","unstructured":"Pasad A, Chou J-C, Livescu K (2022) Layer-wise analysis of a self-supervised speech representation model. arXiv:2107.04734, https:\/\/doi.org\/10.48550\/arXiv.2107.04734","DOI":"10.48550\/arXiv.2107.04734"},{"key":"6158_CR27","doi-asserted-by":"publisher","unstructured":"Pasad A, Chou J-C, Livescu K (2021) Layer-wise analysis of a self-supervised speech representation model. arXiv:2107.04734, https:\/\/doi.org\/10.48550\/arXiv.2107.04734","DOI":"10.48550\/arXiv.2107.04734"},{"key":"6158_CR28","doi-asserted-by":"publisher","unstructured":"Okabe K, Koshinaka T, Shinoda K (2018) Attentive statistics pooling for deep speaker embedding. In: Interspeech 2018, pp 2252\u20132256. arXiv:1803.10963, https:\/\/doi.org\/10.21437\/Interspeech.2018-993","DOI":"10.21437\/Interspeech.2018-993"},{"key":"6158_CR29","doi-asserted-by":"publisher","unstructured":"Gusev A, Volokhov V, Andzhukaev T, Novoselov S, Lavrentyeva G, Volkova M, Gazizullina A, Shulipa A, Gorlanov A, Avdeeva A, Ivanov A, Kozlov A, Pekhovsky T, Matveev Y (2020) Deep speaker embeddings for far-field speaker recognition on short utterances. arXiv:2002.06033, https:\/\/doi.org\/10.48550\/arXiv.2002.06033","DOI":"10.48550\/arXiv.2002.06033"},{"key":"6158_CR30","doi-asserted-by":"publisher","unstructured":"Novoselov S, Lavrentyeva G, Avdeeva A, Volokhov V, Gusev A (2022) Robust speaker recognition with transformers using wav2vec 2.0. arXiv:2203.15095, https:\/\/doi.org\/10.48550\/arXiv.2203.15095","DOI":"10.48550\/arXiv.2203.15095"},{"key":"6158_CR31","doi-asserted-by":"publisher","unstructured":"Goodfellow IJ, Warde-Farley D, Mirza M, Courville A, Bengio Y (2013) Maxout networks. arXiv:1302.4389, https:\/\/doi.org\/10.48550\/arXiv.1302.4389","DOI":"10.48550\/arXiv.1302.4389"},{"key":"6158_CR32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087709","author":"J Deng","year":"2021","unstructured":"Deng J, Guo J, Yang J, Xue N, Kotsia I, Zafeiriou S (2021) ArcFace: additive angular margin loss for deep face recognition. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2021.3087709","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6158_CR33","doi-asserted-by":"publisher","unstructured":"Li L, Nai R, Wang D (2021) Real additive margin softmax for speaker verification.https:\/\/doi.org\/10.48550\/ARXIV.2110.09116","DOI":"10.48550\/ARXIV.2110.09116"},{"key":"6158_CR34","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1016\/0031-3203(90)90098-6","volume":"23","author":"S Shlien","year":"1990","unstructured":"Shlien S (1990) Multiple binary decision tree classifiers. Pattern Recogn 23:757\u2013763. https:\/\/doi.org\/10.1016\/0031-3203(90)90098-6","journal-title":"Pattern Recogn"},{"key":"6158_CR35","doi-asserted-by":"publisher","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. arXiv:1711.05101, https:\/\/doi.org\/10.48550\/arXiv.1711.05101","DOI":"10.48550\/arXiv.1711.05101"},{"key":"6158_CR36","doi-asserted-by":"crossref","unstructured":"Han K, Yu D, Tashev I (2014) Speech emotion recognition using deep neural network and extreme learning machine. In: Interspeech 2014","DOI":"10.21437\/Interspeech.2014-57"},{"key":"6158_CR37","doi-asserted-by":"publisher","unstructured":"Boigne J, Liyanage B, \u00d6strem T (2020) Recognizing more emotions with less data using self-supervised transfer learning. arXiv:2011.05585, https:\/\/doi.org\/10.48550\/arXiv.2011.05585","DOI":"10.48550\/arXiv.2011.05585"},{"key":"6158_CR38","doi-asserted-by":"publisher","unstructured":"Shayaninasab M, Babaali B (2024) Persian speech emotion recognition by fine-tuning transformers. https:\/\/doi.org\/10.48550\/ARXIV.2402.07326","DOI":"10.48550\/ARXIV.2402.07326"},{"key":"6158_CR39","doi-asserted-by":"publisher","unstructured":"Wang Y, Liang Q, Xiao C, Li Y, Moubayed NA, Lin C (2023) Audio Contrastive based fine-tuning. https:\/\/doi.org\/10.48550\/ARXIV.2309.11895","DOI":"10.48550\/ARXIV.2309.11895"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06158-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06158-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06158-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T16:46:58Z","timestamp":1724345218000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06158-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,9]]},"references-count":39,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["6158"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06158-x","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,9]]},"assertion":[{"value":"19 April 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}