{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T09:10:18Z","timestamp":1779009018247,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T00:00:00Z","timestamp":1778371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Science Foundation Ireland","award":["19\\\/FFP\\\/6775"],"award-info":[{"award-number":["19\\\/FFP\\\/6775"]}]},{"name":"Science Foundation Ireland","award":["13\\\/RC\\\/2077_P2"],"award-info":[{"award-number":["13\\\/RC\\\/2077_P2"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,11]]},"DOI":"10.1145\/3774906.3800492","type":"proceedings-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:20:14Z","timestamp":1778250014000},"page":"1316-1329","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SPIDER: Lightweight Speaker Identification on Resource-Constrained Embedded Devices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9456-1092","authenticated-orcid":false,"given":"Markus","family":"Gallacher","sequence":"first","affiliation":[{"name":"Institute of Technical Informatics, Graz University of Technology, Graz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7647-3734","authenticated-orcid":false,"given":"Carlo Alberto","family":"Boano","sequence":"additional","affiliation":[{"name":"Institute of Technical Informatics, Graz University of Technology, Graz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2798-9846","authenticated-orcid":false,"given":"Arun Sankar Muttathu Sivasankara","family":"Pillai","sequence":"additional","affiliation":[{"name":"South East Technological University, Carlow, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4020-0889","authenticated-orcid":false,"given":"Utz","family":"Roedig","sequence":"additional","affiliation":[{"name":"University College Cork, Cork, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0718-0019","authenticated-orcid":false,"given":"Willian","family":"Lunardi","sequence":"additional","affiliation":[{"name":"Technology Innovation Institute, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9202-8582","authenticated-orcid":false,"given":"Michael","family":"Baddeley","sequence":"additional","affiliation":[{"name":"Technology Innovation Institute, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,10]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413564"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"J.P. Campbell. 1997. Speaker recognition: a tutorial. Proceedings of the IEEE 85 9 (1997) 1437\u20131462. 10.1109\/5.628714","DOI":"10.1109\/5.628714"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-9"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207519"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Sanyuan Chen Chengyi Wang Zhengyang Chen Yu Wu Shujie Liu Zhuo Chen Jinyu Li Naoyuki Kanda Takuya Yoshioka Xiong Xiao Jian Wu Long Zhou Shuo Ren Yanmin Qian Yao Qian Jian Wu Michael Zeng Xiangzhan Yu and Furu Wei. 2022. WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing. IEEE Journal of Selected Topics in Signal Processing 16 6 (2022) 1505\u20131518. 10.1109\/JSTSP.2022.3188113","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1294"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-323-91776-6.00016-6"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Junaid\u00a0Iqbal Emon Md\u00a0Ashraful Salek and Khairul\u00a0Taufique Alam. 2025. Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings. https:\/\/arxiv.org\/abs\/2503.10446. 10.48550\/arXiv.2503.10446","DOI":"10.48550\/arXiv.2503.10446"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Ziliang Fan Meng Li Shuo Zhou and Bo Xu. 2020. Exploring wav2vec 2.0 on Speaker Verification and Language Identification. https:\/\/arxiv.org\/abs\/2012.06185. 10.48550\/arXiv.2012.06185","DOI":"10.48550\/arXiv.2012.06185"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940856"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"John\u00a0S. Garofolo Lori\u00a0F. Lamel William\u00a0M. Fisher Jonathan\u00a0G. Fiscus David\u00a0S. Pallett Nancy\u00a0L. Dahlgren and Victor Zue. 1992. TIMIT Acoustic-phonetic Continuous Speech Corpus. Linguistic Data Consortium (11 1992). 10.35111\/17gk-bn40","DOI":"10.35111\/17gk-bn40"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Petko Georgiev Sourav Bhattacharya Nicholas\u00a0D. Lane and Cecilia Mascolo. 2017. Low-resource Multi-task Audio Sensing for Mobile and Embedded Devices via Shared Deep Neural Network Representations. Proceedings of the ACM Interact. Mob. Wearable Ubiquitous Technol. 1 3 Article 50 (Sept. 2017) 19\u00a0pages. 10.1145\/3131895","DOI":"10.1145\/3131895"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1610.02136"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Geoffrey Hinton Li Deng Dong Yu George\u00a0E. Dahl Abdel-rahman Mohamed Navdeep Jaitly Andrew Senior Vincent Vanhoucke Patrick Nguyen Tara\u00a0N. Sainath and Brian Kingsbury. 2012. Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal Processing Magazine 29 6 (2012) 82\u201397.","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053504"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Bei Liu and Yanmin Qian. 2024. Memory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verification. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.01195 (2024). 10.48550\/arXiv.2412.01195","DOI":"10.48550\/arXiv.2412.01195"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Thi-Thanh-Mai Nguyen Duc-Dung Nguyen and Chi-Mai Luong. 2024. Vietnamese Speaker Verification With Mel-Scale Filter Bank Energies and Deep Learning. IEEE Access 12 (2024) 150114\u2013150122. 10.1109\/ACCESS.2024.3479092","DOI":"10.1109\/ACCESS.2024.3479092"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/153687"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0016000"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICALIP.2010.5684389"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.11946"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","unstructured":"Mingxing Tan and Quoc Le. 2021. EfficientNetV2: Smaller Models and Faster Training. 10.48550\/arXiv.2104.00298","DOI":"10.48550\/arXiv.2104.00298"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389750"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Ivette V\u00e9lez Caleb Rascon and Gibr\u00e1n Fuentes-Pineda. 2020. Lightweight speaker verification for online identification of new speakers with short segments. Applied Soft Computing 95 (2020) 106704. 10.1016\/j.asoc.2020.106704","DOI":"10.1016\/j.asoc.2020.106704"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Ching-Chen Wang Ching-Te Chiu and Jheng-Yi Chang. 2022. EfficientNet-eLite: Extremely Lightweight and Efficient CNN Models for Edge Devices by Network Candidate Search. J. Signal Process. Syst. 95 5 (Sept. 2022) 657\u2013669. 10.1007\/s11265-022-01808-w","DOI":"10.1007\/s11265-022-01808-w"},{"key":"e_1_3_3_2_33_2","unstructured":"Hatem Zehir Hafs Toufik and Sara Daas. 2023. TinyCNN: An Embedded CNN Model for Speaker Identification Using ESP32."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Xiaowu Zou Zidong Wang Qi Li and Weiguo Sheng. 2019. Integration of residual network and convolutional neural network along with various activation functions and global pooling for time series classification. Neurocomputing 367 (2019) 39\u201345. 10.1016\/j.neucom.2019.08.023","DOI":"10.1016\/j.neucom.2019.08.023"}],"event":{"name":"SenSys '26: ACM\/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems","location":"Saint Malo France","acronym":"SenSys '26","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","IEEE CS"]},"container-title":["Proceedings of the 2026 ACM\/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774906.3800492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T08:38:10Z","timestamp":1779007090000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774906.3800492"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,10]]},"references-count":33,"alternative-id":["10.1145\/3774906.3800492","10.1145\/3774906"],"URL":"https:\/\/doi.org\/10.1145\/3774906.3800492","relation":{},"subject":[],"published":{"date-parts":[[2026,5,10]]},"assertion":[{"value":"2026-05-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}