{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:46:27Z","timestamp":1742913987295,"version":"3.40.3"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031777301"},{"type":"electronic","value":"9783031777318"}],"license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-77731-8_35","type":"book-chapter","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T16:42:37Z","timestamp":1732034557000},"page":"387-397","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Speech Emotion Recognition: Novel Aggregation Strategies for Self-supervised Features"],"prefix":"10.1007","author":[{"given":"Oscar","family":"Valls","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran","family":"Pastor-Naranjo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roc\u00edo","family":"del Amor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luc\u00eda","family":"G\u00f3mez-Zaragoz\u00e1","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Mar\u00edn-Morales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mariano Alca\u00f1iz","family":"Raya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valery","family":"Naranjo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Berg, A., O\u2019Connor, M., Cruz, M.T.: Keyword Transformer: a Self-attention Model for Keyword Spotting (2021). arXiv preprint arXiv:2104.00769","DOI":"10.21437\/Interspeech.2021-1286"},{"key":"35_CR2","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."},{"issue":"6","key":"35_CR3","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/jstsp.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: Wavlm: large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Signal Process. 16(6), 1505\u20131518 (2022). https:\/\/doi.org\/10.1109\/jstsp.2022.3188113","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"35_CR4","doi-asserted-by":"publisher","unstructured":"Chen, S., et al.: Unispeech-sat: universal speech representation learning with speaker aware pre-training. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6152\u20136156 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747077","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"35_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of Deep Bidirectional Transformers for Language Understanding (2019)"},{"key":"35_CR6","doi-asserted-by":"publisher","unstructured":"Dong, L., Xu, S., Xu, B.: Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5884\u20135888 (2018). https:\/\/doi.org\/10.1109\/ICASSP.2018.8462506","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"35_CR7","unstructured":"Dosovitskiy, A., et al.: An Image is Worth $$16\\times 16$$ Words: Transformers for Image Recognition at Scale (2021)"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Hsu, W.N., Bolte, B., Tsai, Y.H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: Hubert: Self-supervised Speech Representation Learning by Masked Prediction of Hidden Units (2021)","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"35_CR9","doi-asserted-by":"publisher","unstructured":"Jiang, D., et al.: A further study of unsupervised pretraining for transformer based speech recognition. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6538\u20136542 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414539","DOI":"10.1109\/ICASSP39728.2021.9414539"},{"key":"35_CR10","unstructured":"Latif, S., Zaidi, A., Cuayahuitl, H., Shamshad, F., Shoukat, M., Qadir, J.: Transformers in Speech Processing: A Survey (2023)"},{"key":"35_CR11","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models (2023)"},{"key":"35_CR12","unstructured":"Novoselov, S., Lavrentyeva, G., Avdeeva, A., Volokhov, V., Gusev, A.: Robust Speaker Recognition with Transformers Using wav2vec 2.0 (2022)"},{"key":"35_CR13","first-page":"2136","volume":"34","author":"Z Shao","year":"2021","unstructured":"Shao, Z., et al.: Transmil: transformer based correlated multiple instance learning for whole slide image classification. Adv. Neural. Inf. Process. Syst. 34, 2136\u20132147 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Speech Swin-Transformer: Exploring a Hierarchical Transformer with Shifted Windows for Speech Emotion Recognition (2024)","DOI":"10.1109\/ICASSP48485.2024.10447726"}],"container-title":["Lecture Notes in Computer Science","Intelligent Data Engineering and Automated Learning \u2013 IDEAL 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77731-8_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T16:47:21Z","timestamp":1732034841000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77731-8_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"ISBN":["9783031777301","9783031777318"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77731-8_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"14 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IDEAL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Data Engineering and Automated Learning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Valencia","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ideal2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}