{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:19:45Z","timestamp":1742912385927,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819913534"},{"type":"electronic","value":"9789819913541"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-1354-1_10","type":"book-chapter","created":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T14:03:27Z","timestamp":1680098607000},"page":"97-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multimodal Activation Detection Model for\u00a0Wake-Free Robots"],"prefix":"10.1007","author":[{"given":"Hangming","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjiao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,30]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Ahuja, K., Kong, A., Goel, M., Harrison, C.: Direction-of-voice (dov) estimation for intuitive speech interaction with smart devices ecosystems. In: UIST, pp. 1121\u20131131 (2020)","DOI":"10.1145\/3379337.3415588"},{"key":"10_CR2","unstructured":"Chandrasekaran, V., Banerjee, S., Mutlu, B., Fawaz, K.: Powercut and obfuscator: an exploration of the design space for privacy-preserving interventions for voice assistants. arXiv preprint arXiv:1812.00263 (2018)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Wearable microphone jamming. In: Proceedings of the 2020 Chi Conference on Human Factors in Computing Systems, pp. 1\u201312 (2020)","DOI":"10.1145\/3313831.3376304"},{"key":"10_CR4","unstructured":"Coucke, A., et al.: Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. arXiv preprint arXiv:1805.10190 (2018)"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Feng, H., Fawaz, K., Shin, K.G.: Continuous authentication for voice assistants. In: Proceedings of the 23rd Annual International Conference on Mobile Computing and Networking, pp. 343\u2013355 (2017)","DOI":"10.1145\/3117811.3117823"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Hossain, D., Sato, Y.: Efficient corpus design for wake-word detection. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 1094\u20131100. IEEE (2021)","DOI":"10.1109\/SLT48900.2021.9383569"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Iravantchi, Y., Ahuja, K., Goel, M., Harrison, C., Sample, A.: Privacymic: utilizing inaudible frequencies for privacy preserving daily activity recognition. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pp. 1\u201313 (2021)","DOI":"10.1145\/3411764.3445169"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Jose, C., Mishchenko, Y., Senechal, T., Shah, A., Escott, A., Vitaladevuni, S.: Accurate detection of wake word start and end using a CNN. arXiv preprint arXiv:2008.03790 (2020)","DOI":"10.21437\/Interspeech.2020-1491"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Khursheed, M.O., Jose, C., Kumar, R., Fu, G., Kulis, B., Cheekatmalla, S.K.: Tiny-crnn: streaming wakeword detection in a low footprint setting. In: 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 541\u2013547. IEEE (2021)","DOI":"10.1109\/ASRU51503.2021.9688299"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Kumatani, K., Panchapagesan, S., Wu, M., Kim, M., Strom, N., Tiwari, G., Mandai, A.: Direct modeling of raw audio with dnns for wake word detection. In: 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). pp. 252\u2013257. IEEE (2017)","DOI":"10.1109\/ASRU.2017.8268943"},{"issue":"2","key":"10_CR12","doi-asserted-by":"publisher","first-page":"251","DOI":"10.2478\/popets-2020-0026","volume":"2020","author":"AH Mhaidli","year":"2020","unstructured":"Mhaidli, A.H., Venkatesh, M.K., Zou, Y., Schaub, F.: Listen only when spoken to: Interpersonal communication cues as smart speaker privacy controls. Proc. Priv. Enhancing Technol. 2020(2), 251\u2013270 (2020)","journal-title":"Proc. Priv. Enhancing Technol."},{"key":"10_CR13","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":"10_CR14","doi-asserted-by":"crossref","unstructured":"Nie, L., Jia, M., Song, X., Wu, G., Cheng, H., Gu, J.: Multimodal activation: awakening dialog robots without wake words. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 491\u2013500 (2021)","DOI":"10.1145\/3404835.3462964"},{"key":"10_CR15","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Pomykalski, P., Wo\u017aniak, M.P., Wo\u017aniak, P.W., Grudzie\u0144, K., Zhao, S., Romanowski, A.: Considering wake gestures for smart assistant use. In: Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, pp. 1\u20138 (2020)","DOI":"10.1145\/3334480.3383089"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Qin, Y., Yu, C., Li, Z., Zhong, M., Yan, Y., Shi, Y.: Proximic: convenient voice activation via close-to-mic speech detected by a single microphone. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pp. 1\u201312 (2021)","DOI":"10.1145\/3411764.3445687"},{"key":"10_CR18","unstructured":"Roy, N., Shen, S., Hassanieh, H., Choudhury, R.R.: Inaudible voice commands: the $$\\{$$Long-Range$$\\}$$ attack and defense. In: 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18), pp. 547\u2013560 (2018)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lv, H., Povey, D., Xie, L., Khudanpur, S.: Wake word detection with alignment-free lattice-free mmi. arXiv preprint arXiv:2005.08347 (2020)","DOI":"10.21437\/Interspeech.2020-1811"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lv, H., Povey, D., Xie, L., Khudanpur, S.: Wake word detection with streaming transformers. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5864\u20135868. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414777"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Wu, M., et al.: Monophone-based background modeling for two-stage on-device wake word detection. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5494\u20135498. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462227"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Yang, J., Banerjee, G., Gupta, V., Lam, M.S., Landay, J.A.: Soundr: head position and orientation prediction using a microphone array. In: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, pp. 1\u201312 (2020)","DOI":"10.1145\/3313831.3376427"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, X., Su, Z., Rekimoto, J.: Aware: intuitive device activation using prosody for natural voice interactions. In: CHI Conference on Human Factors in Computing Systems, pp. 1\u201316 (2022)","DOI":"10.1145\/3491102.3517687"},{"issue":"6","key":"10_CR24","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.1109\/JSTSP.2022.3182537","volume":"16","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., et al.: Bigssl: exploring the frontier of large-scale semi-supervised learning for automatic speech recognition. IEEE J. Sel. Topics Signal Process. 16(6), 1519\u20131532 (2022)","journal-title":"IEEE J. Sel. Topics Signal Process."}],"container-title":["Communications in Computer and Information Science","Web and Big Data. APWeb-WAIM 2022 International Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1354-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T14:05:00Z","timestamp":1680098700000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1354-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819913534","9789819913541"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1354-1_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","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":"11 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/apweb-waim2022.com\/proceedings","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":"297","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":"75","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":"45","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":"25% - 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","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":"5","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)"}},{"value":"5 Demo papers + 23 workshop papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}