{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:56:32Z","timestamp":1781312192700,"version":"3.54.1"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1203900"],"award-info":[{"award-number":["2023YFF1203900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1203903"],"award-info":[{"award-number":["2023YFF1203903"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332019"],"award-info":[{"award-number":["62332019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20240484513"],"award-info":[{"award-number":["20240484513"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.eswa.2026.132369","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:25:02Z","timestamp":1775579102000},"page":"132369","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DAP-Whisper: A robust audio-visual speech recognition system via distribution-aware prompting and consistency-gated modulation"],"prefix":"10.1016","volume":"322","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4094-492X","authenticated-orcid":false,"given":"Xinyue","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5829-1371","authenticated-orcid":false,"given":"Yakun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0783-684X","authenticated-orcid":false,"given":"Xingyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2088-9308","authenticated-orcid":false,"given":"Changyan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0567-1857","authenticated-orcid":false,"given":"Tao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8286-6785","authenticated-orcid":false,"given":"Liang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2936-2870","authenticated-orcid":false,"given":"Jiangbin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2147-9888","authenticated-orcid":false,"given":"Erwei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.eswa.2026.132369_bib0001","doi-asserted-by":"crossref","first-page":"8717","DOI":"10.1109\/TPAMI.2018.2889052","article-title":"Deep audio-visual speech recognition","volume":"44","author":"Afouras","year":"2018","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"10.1016\/j.eswa.2026.132369_bib0002","unstructured":"Afouras, T., Chung, J. S., & Zisserman, A. (2018b). Lrs3-ted: A large-scale dataset for visual speech recognition. arXiv: 1809.00496."},{"key":"10.1016\/j.eswa.2026.132369_bib0003","series-title":"Icassp 2025-2025 ieee international conference on acoustics, speech and signal processing (icassp)","first-page":"1","article-title":"Large language models are strong audio-visual speech recognition learners","author":"Cappellazzo","year":"2025"},{"key":"10.1016\/j.eswa.2026.132369_bib0004","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12607","article-title":"Leveraging modality-specific representations for audio-visual speech recognition via reinforcement learning","volume":"vol. 37","author":"Chen","year":"2023"},{"key":"10.1016\/j.eswa.2026.132369_bib0005","article-title":"Automatic lip-reading classification using deep learning approaches and optimized quaternion meixner moments by GWO algorithm","volume":"304","author":"El Ogri","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.132369_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18783","article-title":"Watch or listen: Robust audio-visual speech recognition with visual corruption modeling and reliability scoring","author":"Hong","year":"2023"},{"key":"10.1016\/j.eswa.2026.132369_bib0007","series-title":"European conference on computer vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.eswa.2026.132369_bib0008","unstructured":"Jiang, R., Liu, L., & Chen, C. (2024). MoPE: Mixture of prompt experts for parameter-efficient and scalable multimodal fusion. arXiv: 2403.10568."},{"key":"10.1016\/j.eswa.2026.132369_bib0009","doi-asserted-by":"crossref","DOI":"10.1109\/JSTSP.2025.3567838","article-title":"Av-crossnet: An audiovisual complex spectral mapping network for speech separation by leveraging narrow-and cross-band modeling","author":"Kalkhorani","year":"2025","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"10.1016\/j.eswa.2026.132369_bib0010","unstructured":"Kim, S., Cho, S., Bae, S., Jang, K., & Yun, S.-Y. (2025). Multi-task corrupted prediction for learning robust audio-visual speech representation. In International Conference on Learning Representations (ICLR). 91645\u201391666."},{"key":"10.1016\/j.eswa.2026.132369_bib0011","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., & Constant, N. (2021). The power of scale for parameter-efficient prompt tuning. arXiv: 2104.08691.","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"10.1016\/j.eswa.2026.132369_bib0012","unstructured":"Li, X. L., & Liang, P. (2021). Prefix-tuning: Optimizing continuous prompts for generation. arXiv: 2101.00190."},{"key":"10.1016\/j.eswa.2026.132369_bib0013","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2604","article-title":"Efficient multimodal fusion via interactive prompting","author":"Li","year":"2023"},{"key":"10.1016\/j.eswa.2026.132369_bib0014","series-title":"2023 IEEE automatic speech recognition and understanding workshop (ASRU)","first-page":"1","article-title":"Av-data2vec: Self-supervised learning of audio-visual speech representations with contextualized target representations","author":"Lian","year":"2023"},{"key":"10.1016\/j.eswa.2026.132369_bib0015","doi-asserted-by":"crossref","unstructured":"Lim, D., Kim, Y., Kim, D.-H., Yang, D.-H., & Chang, J.-H. (2025). Improving noise robust audio-visual speech recognition via router-gated cross-modal feature fusion. arXiv: 2508.18734.","DOI":"10.1109\/ASRU65441.2025.11434748"},{"key":"10.1016\/j.eswa.2026.132369_bib0016","series-title":"European conference on computer vision","first-page":"740","article-title":"Microsoft Coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.eswa.2026.132369_bib0017","series-title":"Icassp 2025-2025 ieee international conference on acoustics, speech and signal processing (icassp)","first-page":"1","article-title":"Uncovering the visual contribution in audio-visual speech recognition","author":"Lin","year":"2025"},{"key":"10.1016\/j.eswa.2026.132369_bib0018","series-title":"Icassp 2021-2021 ieee international conference on acoustics, speech and signal processing (icassp)","first-page":"7613","article-title":"End-to-end audio-visual speech recognition with conformers","author":"Ma","year":"2021"},{"key":"10.1016\/j.eswa.2026.132369_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.108580","article-title":"Deep learning based multimodal emotion recognition using model-level fusion of audio\u2013visual modalities","volume":"244","author":"Middya","year":"2022","journal-title":"Knowledge-based systems"},{"key":"10.1016\/j.eswa.2026.132369_bib0020","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"27186","article-title":"Unveiling the power of audio-visual early fusion transformers with dense interactions through masked modeling","author":"Mo","year":"2024"},{"key":"10.1016\/j.eswa.2026.132369_bib0021","series-title":"International conference on machine learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.eswa.2026.132369_bib0022","doi-asserted-by":"crossref","unstructured":"Rouditchenko, A., Gong, Y., Thomas, S., Karlinsky, L., Kuehne, H., Feris, R., & Glass, J. (2024). Whisper-flamingo: Integrating visual features into whisper for audio-visual speech recognition and translation. arXiv: 2406.10082.","DOI":"10.21437\/Interspeech.2024-322"},{"key":"10.1016\/j.eswa.2026.132369_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124159","article-title":"Audio\u2013visual speech recognition based on regulated transformer and spatio\u2013temporal fusion strategy for driver assistive systems","volume":"252","author":"Ryumin","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132369_bib0024","unstructured":"Shi, B., Hsu, W.-N., Lakhotia, K., & Mohamed, A. (2022). Learning audio-visual speech representation by masked multimodal cluster prediction. arXiv: 2201.02184."},{"key":"10.1016\/j.eswa.2026.132369_bib0025","series-title":"Icassp 2025-2025 ieee international conference on acoustics, speech and signal processing (icassp)","first-page":"1","article-title":"Adapter-based multi-agent AVSR extension for pre-trained ASR models","author":"Simic","year":"2025"},{"key":"10.1016\/j.eswa.2026.132369_bib0026","unstructured":"Snyder, D., Chen, G., & Povey, D. (2015). Musan: A music, speech, and noise corpus. arXiv: 1510.08484."},{"key":"10.1016\/j.eswa.2026.132369_bib0027","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4711","article-title":"Delving into high-quality synthetic face occlusion segmentation datasets","author":"Voo","year":"2022"},{"key":"10.1016\/j.eswa.2026.132369_bib0028","unstructured":"Wang, F., Yang, S., Shan, S., & Chen, X. (2023). Cooperative dual attention for audio-visual speech enhancement with facial cues. arXiv: 2311.14275."},{"key":"10.1016\/j.eswa.2026.132369_bib0029","series-title":"Icassp 2024-2024 ieee international conference on acoustics, speech and signal processing (icassp)","first-page":"8150","article-title":"Mlca-avsr: Multi-layer cross attention fusion based audio-visual speech recognition","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132369_bib0030","article-title":"Bridging semantics across modalities: Decoupled representation learning for audio-visual speech recognition","author":"Wu","year":"2025","journal-title":"Knowledge-Based Systems"},{"issue":"4","key":"10.1016\/j.eswa.2026.132369_bib0031","doi-asserted-by":"crossref","first-page":"5721","DOI":"10.1007\/s40747-024-01451-x","article-title":"Sla-former: Conformer using shifted linear attention for audio-visual speech recognition","volume":"10","author":"Xiao","year":"2024","journal-title":"Complex & Intelligent Systems"},{"key":"10.1016\/j.eswa.2026.132369_bib0032","doi-asserted-by":"crossref","unstructured":"Xue, J., Liu, X., Wu, X., Yin, X., Huang, D., & Yu, F. (2025). AD-AVSR: Asymmetric dual-stream enhancement for robust audio-visual speech recognition. In Proceedings of the 1st International Workshop & Challenge on Subtle Visual Computing. 3\u201311.","DOI":"10.1145\/3728425.3759905"},{"key":"10.1016\/j.eswa.2026.132369_bib0033","series-title":"Proc. interspeech 2025","first-page":"4938","article-title":"Visually-adaptive guided robust speech recognition with parameter-efficient adaptation","author":"Yang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132369_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126741","article-title":"Target speaker lipreading by audio\u2013visual self-distillation pretraining and speaker adaptation","volume":"272","author":"Zhang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132369_bib0035","unstructured":"Zhang, Y., Han, W., Qin, J., Wang, Y., Bapna, A., Chen, Z., Chen, N., Li, B., Axelrod, V., Wang, G. et al. (2023). Google usm: Scaling automatic speech recognition beyond 100 languages. arXiv: 2303.01037."},{"key":"10.1016\/j.eswa.2026.132369_bib0036","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"27069","article-title":"Es3: Evolving self-supervised learning of robust audio-visual speech representations","author":"Zhang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132369_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16816","article-title":"Conditional prompt learning for vision-language models","author":"Zhou","year":"2022"},{"issue":"9","key":"10.1016\/j.eswa.2026.132369_bib0038","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.132369_bib0039","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"15659","article-title":"Prompt-aligned gradient for prompt tuning","author":"Zhu","year":"2023"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426012820?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426012820?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:07:57Z","timestamp":1781309277000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426012820"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":39,"alternative-id":["S0957417426012820"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132369","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DAP-Whisper: A robust audio-visual speech recognition system via distribution-aware prompting and consistency-gated modulation","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132369","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132369"}}