{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:26:46Z","timestamp":1776889606907,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3688980","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"11342-11347","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0021-5661","authenticated-orcid":false,"given":"Ruijie","family":"Tao","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapre, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9581-1996","authenticated-orcid":false,"given":"Zhan","family":"Shi","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2317-9571","authenticated-orcid":false,"given":"Yidi","family":"Jiang","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1767-7598","authenticated-orcid":false,"given":"Duc-Tuan","family":"Truong","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6257-7399","authenticated-orcid":false,"given":"Eng-Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4127-8258","authenticated-orcid":false,"given":"Massimo","family":"Alioto","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-41"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0020--7373(81)80001--6"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020--2229"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Joon Son Chung Arsha Nagrani and Andrew Zisserman. 2018. VoxCeleb2: Deep Speaker Recognition. In Interspeech. 1086--1090.","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1065"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987720"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.113114"},{"key":"e_1_3_2_1_9_1","volume-title":"HLT-NUS Submission for 2019 NIST Multimedia Speaker Recognition Evaluation. In 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). 605--609","author":"Das Rohan Kumar","year":"2020","unstructured":"Rohan Kumar Das, Ruijie Tao, Jichen Yang, Wei Rao, Cheng Yu, and Haizhou Li. 2020. HLT-NUS Submission for 2019 NIST Multimedia Speaker Recognition Evaluation. In 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). 605--609."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_2_1_11_1","volume-title":"Retinaface: Single-stage dense face localisation in the wild. arXiv preprint arXiv:1905.00641","author":"Deng Jiankang","year":"2019","unstructured":"Jiankang Deng, Jia Guo, Yuxiang Zhou, Jinke Yu, Irene Kotsia, and Stefanos Zafeiriou. 2019. Retinaface: Single-stage dense face localisation in the wild. arXiv preprint arXiv:1905.00641 (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Brecht Desplanques Jenthe Thienpondt and Kris Demuynck. 2020. ECAPA-TDNN: Emphasized Channel Attention propagation and aggregation in TDNN based speaker verification. In Interspeech. 3830--3834.","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446072"},{"key":"e_1_3_2_1_15_1","volume-title":"Target Speech Diarization with Multimodal Prompts. arXiv preprint arXiv:2406.07198","author":"Jiang Yidi","year":"2024","unstructured":"Yidi Jiang, Ruijie Tao, Zhengyang Chen, Yanmin Qian, and Haizhou Li. 2024. Target Speech Diarization with Multimodal Prompts. arXiv preprint arXiv:2406.07198 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Target active speaker detection with audio-visual cues. arXiv preprint arXiv:2305.12831","author":"Jiang Yidi","year":"2023","unstructured":"Yidi Jiang, Ruijie Tao, Zexu Pan, and Haizhou Li. 2023. Target active speaker detection with audio-visual cues. arXiv preprint arXiv:2305.12831 (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3084299"},{"key":"e_1_3_2_1_18_1","first-page":"50221","article-title":"Disentangling voice and content with self-supervision for speaker recognition","volume":"36","author":"Liu Tianchi","year":"2023","unstructured":"Tianchi Liu, Kong Aik Lee, Qiongqiong Wang, and Haizhou Li. 2023. Disentangling voice and content with self-supervision for speaker recognition. Advances in Neural Information Processing Systems, Vol. 36 (2023), 50221--50236.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"Yi Ma, Ruijie Tao, and Haizhou Li.","author":"Liu Tianchi","year":"2024","unstructured":"Tianchi Liu, Lin Zhang, Rohan Kumar Das, Yi Ma, Ruijie Tao, and Haizhou Li. 2024. How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio? arXiv preprint arXiv:2406.02483 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"Learnable PINs: Cross-Modal Embeddings for Person Identity. In European Conference on Computer Vision.","author":"Nagrani A.","unstructured":"A. Nagrani, S. Albanie, and A. Zisserman. 2018. Learnable PINs: Cross-Modal Embeddings for Person Identity. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"e_1_3_2_1_22_1","volume-title":"Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Nagrani Arsha","year":"2018","unstructured":"Arsha Nagrani, Samuel Albanie, and Andrew Zisserman. 2018. Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018), 8427--8436."},{"key":"e_1_3_2_1_23_1","volume-title":"Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Nagrani Arsha","year":"2018","unstructured":"Arsha Nagrani, Samuel Albanie, and Andrew Zisserman. 2018 d. Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018), 8427--8436."},{"key":"e_1_3_2_1_24_1","volume-title":"Joon Son Chung, and Andrew Zisserman","author":"Nagrani Arsha","year":"2017","unstructured":"Arsha Nagrani, Joon Son Chung, and Andrew Zisserman. 2017. VoxCeleb: A Large-Scale Speaker Identification Dataset. In Interspeech. 2616--2620."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3061800"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-48312-7_2"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-38"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747704"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097207"},{"key":"e_1_3_2_1_31_1","volume-title":"Cross-modal Speaker Verification and Recognition: A Multilingual Perspective. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Saeed Muhammad Saad","year":"2020","unstructured":"Muhammad Saad Saeed, Shah Nawaz, Pietro Morerio, A. Mahmood, Ignazio Gallo, Muhammad Haroon Yousaf, and Alessio Del Bue. 2020. Cross-modal Speaker Verification and Recognition: A Multilingual Perspective. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2020), 1682--1691."},{"key":"e_1_3_2_1_32_1","volume-title":"Rohan Kumar Das, Muhammad Zaigham Zaheer, Marta Moscati, Markus Schedl, Muhammad Haris Khan, Karthik Nandakumar, and Muhammad Haroon Yousaf.","author":"Saeed Muhammad Saad","year":"2024","unstructured":"Muhammad Saad Saeed, Shah Nawaz, Muhammad Salman Tahir, Rohan Kumar Das, Muhammad Zaigham Zaheer, Marta Moscati, Markus Schedl, Muhammad Haris Khan, Karthik Nandakumar, and Muhammad Haroon Yousaf. 2024. Face-voice Association in Multilingual Environments (FAME) Challenge 2024 Evaluation Plan. arXiv preprint arXiv:2404.09342 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414260"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAI58407.2023.10136626"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"e_1_3_2_1_36_1","volume-title":"Rohan Kumar Das, and Haizhou Li","author":"Tao Ruijie","year":"2020","unstructured":"Ruijie Tao, Rohan Kumar Das, and Haizhou Li. 2020. Audio-visual Speaker Recognition with a Cross-modal Discriminative Network. In Interspeech 2020."},{"key":"e_1_3_2_1_37_1","volume-title":"Voice Conversion Augmentation for Speaker Recognition on Defective Datasets. arXiv preprint arXiv:2404.00863","author":"Tao Ruijie","year":"2024","unstructured":"Ruijie Tao, Zhan Shi, Yidi Jiang, Tianchi Liu, and Haizhou Li. 2024. Voice Conversion Augmentation for Speaker Recognition on Defective Datasets. arXiv preprint arXiv:2404.00863 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979878"},{"key":"e_1_3_2_1_39_1","volume-title":"Kong Aik Lee, and Eng Siong Chng","author":"Truong Duc-Tuan","year":"2024","unstructured":"Duc-Tuan Truong, Ruijie Tao, Tuan Nguyen, Hieu-Thi Luong, Kong Aik Lee, and Eng Siong Chng. 2024. Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection. arxiv: 2406.17376 [cs.SD] https:\/\/arxiv.org\/abs\/2406.17376"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447160"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383459"},{"key":"e_1_3_2_1_42_1","volume-title":"Cam: A fast and efficient network for speaker verification using context-aware masking. arXiv preprint arXiv:2303.00332","author":"Wang Hui","year":"2023","unstructured":"Hui Wang, Siqi Zheng, Yafeng Chen, Luyao Cheng, and Qian Chen. 2023. Cam: A fast and efficient network for speaker verification using context-aware masking. arXiv preprint arXiv:2303.00332 (2023)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688980","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3688980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:28Z","timestamp":1750295848000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688980"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":42,"alternative-id":["10.1145\/3664647.3688980","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3688980","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}