{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:04:34Z","timestamp":1764842674768,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031204999"},{"type":"electronic","value":"9783031205002"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-20500-2_27","type":"book-chapter","created":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T05:12:32Z","timestamp":1672549952000},"page":"327-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Audio-Visual Multi-person Keyword Spotting via\u00a0Hybrid Fusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5912-7669","authenticated-orcid":false,"given":"Yuxin","family":"Su","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2414-3674","authenticated-orcid":false,"given":"Ziling","family":"Miao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7498-6541","authenticated-orcid":false,"given":"Hong","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,1]]},"reference":[{"issue":"8","key":"27_CR1","doi-asserted-by":"publisher","first-page":"1618","DOI":"10.1109\/TASLP.2017.2703650","volume":"25","author":"C Pang","year":"2017","unstructured":"Pang, C., Liu, H., Zhang, J., Li, X.: Binaural sound localization based on reverberation weighting and generalized parametric mapping. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(8), 1618\u20131632 (2017). https:\/\/doi.org\/10.1109\/TASLP.2017.2703650","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"doi-asserted-by":"publisher","unstructured":"W\u00f6llmer, M., Eyben, F., Keshet, J., Graves, A., Schuller, B., Rigoll, G.: Robust discriminative keyword spotting for emotionally colored spontaneous speech using bidirectional LSTM networks, pp. 3949\u20133952 (2009). https:\/\/doi.org\/10.1109\/ICASSP.2009.4960492","key":"27_CR2","DOI":"10.1109\/ICASSP.2009.4960492"},{"doi-asserted-by":"publisher","unstructured":"Karakos, D., et al.: Score normalization and system combination for improved keyword spotting. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 210\u2013215 (2013). https:\/\/doi.org\/10.1109\/ASRU.2013.6707731","key":"27_CR3","DOI":"10.1109\/ASRU.2013.6707731"},{"doi-asserted-by":"crossref","unstructured":"Kim, B., Chang, S., Lee, J., Sung, D.: Broadcasted residual learning for efficient keyword spotting. arXiv preprint arXiv:2106.04140 (2021)","key":"27_CR4","DOI":"10.21437\/Interspeech.2021-383"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, H., Tang, H.: Multi-modal perception attention network with self-supervised learning for audio-visual speaker tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 1456\u20131463 (2022)","key":"27_CR5","DOI":"10.1609\/aaai.v36i2.20035"},{"doi-asserted-by":"publisher","unstructured":"Zheng, H., Wang, M., Li, Z.: Audio-visual speaker identification with multi-view distance metric learning, pp. 4561\u20134564 (2010). https:\/\/doi.org\/10.1109\/ICIP.2010.5653016","key":"27_CR6","DOI":"10.1109\/ICIP.2010.5653016"},{"issue":"2","key":"27_CR7","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1109\/TCYB.2013.2250954","volume":"44","author":"D Stewart","year":"2014","unstructured":"Stewart, D., Seymour, R., Pass, A., Ming, J.: Robust audio-visual speech recognition under noisy audio-video conditions. IEEE Trans. Cybern. 44(2), 175\u2013184 (2014). https:\/\/doi.org\/10.1109\/TCYB.2013.2250954","journal-title":"IEEE Trans. Cybern."},{"doi-asserted-by":"crossref","unstructured":"Miao, Y., Gowayyed, M., Metze, F.: EESEN: end-to-end speech recognition using deep RNN models and WFST-based decoding. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 167\u2013174. IEEE (2015)","key":"27_CR8","DOI":"10.1109\/ASRU.2015.7404790"},{"doi-asserted-by":"crossref","unstructured":"L\u00f3pez-Espejo, I., Tan, Z.H., Hansen, J., Jensen, J.: Deep spoken keyword spotting: an overview. IEEE Access (2021)","key":"27_CR9","DOI":"10.1109\/ACCESS.2021.3139508"},{"issue":"3","key":"27_CR10","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1109\/TMM.2016.2520091","volume":"18","author":"P Wu","year":"2016","unstructured":"Wu, P., Liu, H., Li, X., Fan, T., Zhang, X.: A novel lip descriptor for audio-visual keyword spotting based on adaptive decision fusion. IEEE Trans. Multimedia 18(3), 326\u2013338 (2016)","journal-title":"IEEE Trans. Multimedia"},{"doi-asserted-by":"crossref","unstructured":"Ding, R., Pang, C., Liu, H.: Audio-visual keyword spotting based on multidimensional convolutional neural network. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 4138\u20134142. IEEE (2018)","key":"27_CR11","DOI":"10.1109\/ICIP.2018.8451096"},{"unstructured":"Momeni, L., Afouras, T., Stafylakis, T., Albanie, S., Zisserman, A.: Seeing wake words: audio-visual keyword spotting. arXiv preprint arXiv:2009.01225 (2020)","key":"27_CR12"},{"issue":"9","key":"27_CR13","doi-asserted-by":"publisher","first-page":"1635","DOI":"10.1109\/JPROC.2015.2459017","volume":"103","author":"AK Katsaggelos","year":"2015","unstructured":"Katsaggelos, A.K., Bahaadini, S., Molina, R.: Audiovisual fusion: challenges and new approaches. Proc. IEEE 103(9), 1635\u20131653 (2015). https:\/\/doi.org\/10.1109\/JPROC.2015.2459017","journal-title":"Proc. IEEE"},{"doi-asserted-by":"publisher","unstructured":"Liu, H., Li, W., Yang, B.: Robust audio-visual speech recognition based on hybrid fusion. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 7580\u20137586 (2021). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412817","key":"27_CR14","DOI":"10.1109\/ICPR48806.2021.9412817"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)","key":"27_CR15"},{"unstructured":"Kim, J., Jun, J., Zhang, B.: Bilinear attention networks. CoRR (2018). arXiv:1805.07932","key":"27_CR16"},{"doi-asserted-by":"crossref","unstructured":"Braga, O., Siohan, O.: A closer look at audio-visual multi-person speech recognition and active speaker selection. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6863\u20136867. IEEE (2021)","key":"27_CR17","DOI":"10.1109\/ICASSP39728.2021.9414160"},{"unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2018)","key":"27_CR18"},{"doi-asserted-by":"crossref","unstructured":"Petridis, S., Stafylakis, T., Ma, P., Cai, F., Tzimiropoulos, G., Pantic, M.: End-to-end audiovisual speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6548\u20136552. IEEE (2018)","key":"27_CR19","DOI":"10.1109\/ICASSP.2018.8461326"},{"unstructured":"Chen, S., et al.: WavLM: large-scale self-supervised pre-training for full stack speech processing. arXiv preprint arXiv:2110.13900 (2021)","key":"27_CR20"},{"doi-asserted-by":"crossref","unstructured":"Shi, B., Hsu, W.N., Mohamed, A.: Robust self-supervised audio-visual speech recognition. arXiv preprint arXiv:2201.01763 (2022)","key":"27_CR21","DOI":"10.21437\/Interspeech.2022-99"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20500-2_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T05:37:22Z","timestamp":1672551442000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20500-2_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031204999","9783031205002"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20500-2_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.cn\/#\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"472","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"164","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.1","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}