{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:09:00Z","timestamp":1743124140768,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031779602"},{"type":"electronic","value":"9783031779619"}],"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\/978-3-031-77961-9_12","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T13:54:32Z","timestamp":1732197272000},"page":"163-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OpenAV: Bilingual Dataset for Audio-Visual Voice Control of a Computer for Hand Disabled People"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0412-7765","authenticated-orcid":false,"given":"Denis","family":"Ivanko","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7935-0569","authenticated-orcid":false,"given":"Dmitry","family":"Ryumin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7479-2851","authenticated-orcid":false,"given":"Alexandr","family":"Axyonov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6503-1447","authenticated-orcid":false,"given":"Alexey","family":"Kashevnik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3424-652X","authenticated-orcid":false,"given":"Alexey","family":"Karpov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Karpov, A., Ronzhin, A., Kipyatkova, I.: An assistive bi-modal user interface integrating multi-channel speech recognition and computer vision. In: Human-Computer Interaction. Interaction Techniques and Environments: 14th International Conference, HCI International 2011, Orlando, FL, USA, July 9\u201314, 2011, Proceedings, Part II 14, pp. 454\u2013463 (2011)","DOI":"10.1007\/978-3-642-21605-3_50"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Wang, J., et. al.: Restoring speaking lips from occlusion for audio-visual speech recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 17, pp. 19144\u201319152 (2024)","DOI":"10.1609\/aaai.v38i17.29882"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Ma, P., Petridis, S., Pantic, M.: End-to-end audio-visual speech recognition with conformers. In: ICASSP 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7613\u20137617 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Ryumin, D., et. al.: Audio\u2013visual speech recognition based on regulated transformer and spatio\u2013temporal fusion strategy for driver assistive systems. In: Expert Systems with Applications, vol. 252, p. 124159 (2024)","DOI":"10.1016\/j.eswa.2024.124159"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Shi, B., Hsu, W. N., Mohamed, A.: Robust self-supervised audio-visual speech recognition. In: Interspeech 2022 (2022)","DOI":"10.21437\/Interspeech.2022-99"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Burchi, M., et. al.: Multilingual audio-visual speech recognition with hybrid CTC\/RNN-T fast conformer. In: ICASSP 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10211\u201310215 (2024)","DOI":"10.1109\/ICASSP48485.2024.10445891"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Chen, C., et. al.: Leveraging modality-specific representations for audio-visual speech recognition via reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 11, pp. 12607\u201312615 (2023)","DOI":"10.1609\/aaai.v37i11.26484"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Fernandez-Lopez, A., Sukno, F. M.: Survey on automatic lip-reading in the era of deep learning. In: Image and Vision Computing, vol. 78, pp. 53\u201372 (2018)","DOI":"10.1016\/j.imavis.2018.07.002"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Ivanko, D., Ryumin, D., Karpov, A.: A review of recent advances on deep learning methods for audio-visual speech recognition. Mathematics, 11(12), 2665 (2023)","DOI":"10.3390\/math11122665"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Wang, X., et. al.: CATNet: cross-modal fusion for audio\u2013visual speech recognition. Pattern Recogn. Lett. 178, 216\u2013222 (2024)","DOI":"10.1016\/j.patrec.2024.01.002"},{"key":"12_CR11","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Computer Vision\u2013ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20\u201324, 2016, Revised Selected Papers, Part II 13, pp. 87\u2013103 (2017)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Chung, J.S., et. al.: Lip reading sentences in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6447\u20136456 (2018)","DOI":"10.1109\/CVPR.2017.367"},{"key":"12_CR13","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: LRS3-TED: a large-scale dataset for visual speech recognition. In: arXiv preprint arXiv:1809.00496 (2018)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Anwar, M., et. al.: MuAViC: a multilingual audio-visual corpus for robust speech recognition and robust speech-to-text translation. In: Interspeech 2023, pp. 4064\u20134068 (2023)","DOI":"10.21437\/Interspeech.2023-2279"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Wang, J., et. al.: MAVD: the first open large-scale mandarin audio-visual dataset with depth information. In: Interspeech 2023, pp. 2112\u20132117 (2023)","DOI":"10.21437\/Interspeech.2023-823"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Verkhodanova, V., et. al.: HAVRUS corpus: high-speed recordings of audio-visual Russian speech. In: Speech and Computer: 18th International Conference, SPECOM 2016, Budapest, Hungary, August 23\u201327, 2016, Proceedings 18, pp. 338\u2013345 (2016)","DOI":"10.1007\/978-3-319-43958-7_40"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xu, R., Song, M.: A cascade sequence-to-sequence model for Chinese Mandarin lip reading. In: Proceedings of the ACM Multimedia Asia, pp. 1\u20136 (2019)","DOI":"10.1145\/3338533.3366579"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Alghamdi, N., et. al.: A corpus of audio-visual Lombard speech with frontal and profile views. J. Acoust. Soc. Am. 143(6), 523\u2013529 (2018)","DOI":"10.1121\/1.5042758"},{"key":"12_CR19","unstructured":"Ivanko, D., et. al.: RUSAVIC corpus: Russian audio-visual speech in cars. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference (LREC), pp. 1555\u20131559 (2022)"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Ryumin, D., Ivanko, D., Ryumina, E.: Audio-visual speech and gesture recognition by sensors of mobile devices. Sensors 23(4), 2284 (2023)","DOI":"10.3390\/s23042284"},{"key":"12_CR21","unstructured":"Lugaresi, C., et. al.: Mediapipe: a framework for perceiving and processing reality. In: Third Workshop on Computer Vision for AR\/VR at IEEE Computer Vision and Pattern Recognition (CVPR) (2019)"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"McFee, B., et. al.: librosa: audio and music signal analysis in Python. In: Proceedings of the 14th Python in Science Conference, vol. 8, pp. 18\u201325 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Zhong, Z., et. al.: Squeeze-and-attention networks for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13065\u201313074 (2020)","DOI":"10.1109\/CVPR42600.2020.01308"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77961-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T14:05:21Z","timestamp":1732197921000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77961-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031779602","9783031779619"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77961-9_12","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"}}]}}