{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:23:53Z","timestamp":1743027833770,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031780134"},{"type":"electronic","value":"9783031780141"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-78014-1_3","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:25:26Z","timestamp":1732191926000},"page":"30-42","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Enhanced Compact Convolution Transformer for\u00a0Age, Gender and\u00a0Emotion Detection in\u00a0Egyptian Arabic Speech"],"prefix":"10.1007","author":[{"given":"Aya","family":"Abdalla","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nada","family":"Sharaf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caroline","family":"Sabty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.specom.2020.04.005","volume":"122","author":"L Abdel-Hamid","year":"2020","unstructured":"Abdel-Hamid, L.: Egyptian Arabic speech emotion recognition using prosodic, spectral and wavelet features. Speech Commun. 122, 19\u201330 (2020)","journal-title":"Speech Commun."},{"key":"3_CR2","unstructured":"Seknedy El, M., Fawzi, S.A.: Emotion recognition system for Arabic speech: case study Egyptian accent. In: International Conference on Model and Data Engineering (2022)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Safwat, S., et al.: Building an Egyptian-Arabic speech corpus for emotion analysis using deep learning. In: Pacific Rim International Conference on Artificial Intelligence (2023)","DOI":"10.1007\/978-981-99-7025-4_28"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Nasr, L.I., et al.: Survey on Arabic speech emotion recognition. Int. J. Speech Technol. 27, 53\u201368 (2024)","DOI":"10.1007\/s10772-024-10088-7"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Rakan, R., et al.: Advancing Egyptian Arabic speech emotion recognition: insights from 2D representations and model evaluations. In: 2023 Eleventh International Conference on Intelligent Computing and Information Systems (ICICIS), pp. 154\u2013159 (2023)","DOI":"10.1109\/ICICIS58388.2023.10391184"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Aljuhani, R.H., et al.: Arabic speech emotion recognition from Saudi dialect corpus. IEEE Access 9, 127081\u2013127085 (2021)","DOI":"10.1109\/ACCESS.2021.3110992"},{"key":"3_CR7","doi-asserted-by":"publisher","unstructured":"Alamri, H., Alshanbari, H.: Emotion Recognition in Arabic Speech From Saudi Dialect Corpus Using Machine Learning and Deep Learning Algorithms, 13 June 2023, PREPRINT (Version 1) available at Research Square https:\/\/doi.org\/10.21203\/rs.3.rs-3019159\/v1","DOI":"10.21203\/rs.3.rs-3019159\/v1"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Shahin, I., et al.: Emotion recognition using hybrid gaussian mixture model and deep neural network. IEEE Access 7, 26777\u201326787 (2019)","DOI":"10.1109\/ACCESS.2019.2901352"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Shahin, I., et al.: An efficient feature selection method for Arabic and English speech emotion recognition using Grey Wolf Optimizer. Appl. Acoust. 205, 109279 (2023)","DOI":"10.1016\/j.apacoust.2023.109279"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Ali, G., et al.: Recognizing speech emotions in Iraqi dialect using machine learning techniques. In: 2022 International Conference on Emerging Trends in Computing and Engineering Applications (ETCEA), pp. 1\u20135 (2022)","DOI":"10.1109\/ETCEA57049.2022.10009780"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Yuan, K., et al.: Incorporating convolution designs into visual transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 559\u2013568 (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"3_CR12","unstructured":"Dosovitskiy, A., et al.: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ArXiv abs\/2010.11929 (2020)"},{"key":"3_CR13","unstructured":"Hassani, A., et al.: Escaping the Big Data Paradigm with Compact Transformers. ArXiv abs\/2104.05704 (2021)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Khan, S.H., et al.: Transformers in vision: a survey. ACM Comput. Surv. (CSUR) 54, 1\u201341 (2021)","DOI":"10.1145\/3505244"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Arezzo, A., Berretti, S.: SPEAKER VGG CCT: cross-corpus speech emotion recognition with speaker embedding and vision transformers. In: Proceedings of the 4th ACM International Conference on Multimedia in Asia (2022)","DOI":"10.1145\/3551626.3564937"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Akinpelu, S., et al.: An enhanced speech emotion recognition using vision transformer. Sci. Rep. 14, 13126 (2024)","DOI":"10.1038\/s41598-024-63776-4"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Agrima, A., et al.: Emotion recognition from Moroccan dialect speech and energy band distribution. In: 2019 International Conference on Wireless Technologies, Embedded and Intelligent Systems (WITS), pp. 1\u20136 (2019)","DOI":"10.1109\/WITS.2019.8723775"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CvT: introducing Convolutions to Vision Transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Nabil, M., Abdalla, A., Sharaf, N., Sabty, C.: Bridging the gap: developing an automatic speech recognition system for Egyptian dialect integration into chatbots. In: 29th International Conference on Applications of Natural Language to Information Systems, NLDB (2024)","DOI":"10.1007\/978-3-031-70242-6_12"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Z.-Q., Ivan, J.T.: Learning utterance-level representations for speech emotion and age\/gender recognition using deep neural networks. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5150\u20135154 (2017)","DOI":"10.1109\/ICASSP.2017.7953138"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Furey, E., Blue, J.: Alexa, Emotions, Privacy and GDPR (2018)","DOI":"10.14236\/ewic\/HCI2018.212"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Dahmani, H., et al.: Natural Arabic language resources for emotion recognition in Algerian dialect. In: International Colloquium on Automata, Languages and Programming (2019)","DOI":"10.1007\/978-3-030-32959-4_2"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78014-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T15:06:09Z","timestamp":1736348769000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78014-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031780134","9783031780141"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78014-1_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","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":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}