{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:45:12Z","timestamp":1760255112186,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032079558","type":"print"},{"value":"9783032079565","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-07956-5_7","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:40Z","timestamp":1760253580000},"page":"101-112","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spoken Emotion Recognition Using Soft Labels"],"prefix":"10.1007","author":[{"given":"D\u00e1niel","family":"Halmai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G\u00e1bor","family":"Gosztolya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"issue":"3","key":"7_CR1","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1016\/j.csl.2010.10.001","volume":"25","author":"EM Albornoz","year":"2011","unstructured":"Albornoz, E.M., Milone, D.H., Rufiner, H.L.: Spoken emotion recognition using hierarchical classifiers. Comput. Speech Lang. 25(3), 556\u2013570 (2011)","journal-title":"Comput. Speech Lang."},{"key":"7_CR2","unstructured":"Babu, A., et al.: XLS-R: self-supervised cross-lingual speech representation learning at scale. CoRR abs\/2111.09296 (2021). https:\/\/arxiv.org\/abs\/2111.09296"},{"key":"7_CR3","unstructured":"Baevski, A., Zhou, H., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations (2020). https:\/\/arxiv.org\/abs\/2006.11477"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W.F., Weiss, B., et\u00a0al.: A database of German emotional speech. In: Proceedings of Interspeech, pp. 1517\u20131520 (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"key":"7_CR5","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., et al.: IEMOCAP: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42, 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Chen, M., et\u00a0al.: 1st place solution to odyssey emotion recognition challenge task1: tackling class imbalance problem. arXiv preprint arXiv:2405.20064 (2024)","DOI":"10.21437\/odyssey.2024-37"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Conneau, A., Baevski, A., Collobert, R., Mohamed, A., Auli, M.: Unsupervised cross-lingual representation learning for speech recognition (2020). https:\/\/arxiv.org\/abs\/2006.13979","DOI":"10.21437\/Interspeech.2021-329"},{"key":"7_CR8","doi-asserted-by":"publisher","unstructured":"Dellaert, F., Polzin, T., Waibel, A.: Recognizing emotion in speech. In: Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP 1996, vol.\u00a03, pp. 1970\u20131973 (1996). https:\/\/doi.org\/10.1109\/ICSLP.1996.608022","DOI":"10.1109\/ICSLP.1996.608022"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Duret, J., Rouvier, M., Est\u00e9ve, Y.: MSP-podcast SER challenge 2024: L\u2019antenne du ventoux multimodal self-supervised learning for speech emotion recognition. In: Proceedings of Odyssey, pp. 309\u2013314. Quebec City (2024)","DOI":"10.21437\/odyssey.2024-44"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Fayek, H., Lech, M., Cavedon, L.: Modeling subjectiveness in emotion recognition with deep neural networks: ensembles vs soft labels. In: Proceedings of IJCNN, pp. 566\u2013570. Vancouver (2016)","DOI":"10.1109\/IJCNN.2016.7727250"},{"key":"7_CR11","unstructured":"Goncalves, L., et al.: Odyssey 2024-speech emotion recognition challenge: dataset, baseline framework, and results. Development 10(9,290), 4\u201354 (2024)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Han, W., Ruan, H., Chen, X., Wang, Z., Li, H., Schuller, B.: Towards temporal modelling of categorical speech emotion recognition. In: Proceedings of Interspeech, pp. 932\u2013936. Hyderabad (2018)","DOI":"10.21437\/Interspeech.2018-1858"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Keesing, A., Koh, Y.S., Witbrock, M.: Acoustic features and neural representations for categorical emotion recognition from speech. In: Proceedings of Interspeech, pp. 3415\u20133419. Brno (2021)","DOI":"10.21437\/Interspeech.2021-2217"},{"key":"7_CR14","doi-asserted-by":"publisher","unstructured":"Khalil, R.A., Jones, E., Babar, M.I., Jan, T., Zafar, M.H., Alhussain, T.: Speech emotion recognition using deep learning techniques: a review. IEEE Access 7, 117327\u2013117345 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2936124","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"7_CR15","doi-asserted-by":"publisher","unstructured":"Li, D., Liu, J., Yang, Z., Sun, L., Wang, Z.: Speech emotion recognition using recurrent neural networks with directional self-attention. Expert Syst. Appl. 173, 114683 (2021). https:\/\/doi.org\/10.1016\/j.eswa.2021.114683, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S095741742100124X","DOI":"10.1016\/j.eswa.2021.114683"},{"key":"7_CR16","doi-asserted-by":"publisher","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), 1\u201335 (2018). https:\/\/doi.org\/10.1371\/journal.pone.0196391","DOI":"10.1371\/journal.pone.0196391"},{"issue":"4","key":"7_CR17","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.: Building naturalistic emotionally balanced speech corpus by retrieving emotional speech from existing podcast recordings. IEEE Trans. Affect. Comput. 10(4), 471\u2013483 (2019). https:\/\/doi.org\/10.1109\/TAFFC.2017.2736999","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"7_CR18","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1214\/aoms\/1177730491","volume":"18","author":"HB Mann","year":"1947","unstructured":"Mann, H.B., Whitney, D.R.: On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Stat. 18(1), 50\u201360 (1947)","journal-title":"Ann. Math. Stat."},{"key":"7_CR19","unstructured":"Ravanelli, M., et al.: SpeechBrain: a general-purpose speech toolkit (2021). arXiv:2106.04624"},{"issue":"3","key":"7_CR20","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/S0892-1997(05)80231-0","volume":"9","author":"KR Scherer","year":"1995","unstructured":"Scherer, K.R.: Expression of emotion in voice and music. J. Voice 9(3), 235\u2013248 (1995)","journal-title":"J. Voice"},{"issue":"3","key":"7_CR21","doi-asserted-by":"publisher","first-page":"1539","DOI":"10.1109\/TAFFC.2024.3360428","volume":"15","author":"SG Upadhyay","year":"2024","unstructured":"Upadhyay, S.G., Chien, W.S., Su, B.H., Lee, C.C.: Learning with rater-expanded label space to improve speech emotion recognition. IEEE Trans. Affect. Comput. 15(3), 1539\u20131552 (2024)","journal-title":"IEEE Trans. Affect. Comput."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07956-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:44Z","timestamp":1760253584000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07956-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032079558","9783032079565"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07956-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"13 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Szeged","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom.inf.u-szeged.hu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}