{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:24Z","timestamp":1750309464087,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"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":[[2024,12,13]]},"DOI":"10.1145\/3702250.3702293","type":"proceedings-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T12:11:38Z","timestamp":1735647098000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust Speech Recognition with Unsupervised Frame and Character Level Adversarial Domain Matching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3548-2663","authenticated-orcid":false,"given":"Soumen","family":"Paul","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1435-6051","authenticated-orcid":false,"given":"Partha Pratim","family":"Das","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, IN"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6112-6887","authenticated-orcid":false,"given":"Krothapalli","family":"Sreenivasa Rao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India"}]}],"member":"320","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178934"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953145"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Tao Bai Jinqi Luo Jun Zhao Bihan Wen and Qian Wang. 2021. Recent advances in adversarial training for adversarial robustness. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2102.01356 (2021).","DOI":"10.24963\/ijcai.2021\/591"},{"key":"e_1_3_3_1_5_2","first-page":"1","volume-title":"Speech Communication; 13th ITG-Symposium","author":"Denisov Pavel","year":"2018","unstructured":"Pavel Denisov, Ngoc\u00a0Thang Vu, and Marc\u00a0Ferras Font. 2018. Unsupervised domain adaptation by adversarial learning for robust speech recognition. In Speech Communication; 13th ITG-Symposium. VDE, 1\u20135."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Hongqiang Du Lei Xie and Haizhou Li. 2022. Noise-robust voice conversion with domain adversarial training. Neural Networks 148 (2022) 74\u201384.","DOI":"10.1016\/j.neunet.2022.01.003"},{"key":"e_1_3_3_1_7_2","unstructured":"Yaroslav Ganin Evgeniya Ustinova Hana Ajakan Pascal Germain Hugo Larochelle Fran\u00e7ois Laviolette Mario March and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. Journal of machine learning research 17 59 (2016) 1\u201335."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854362"},{"key":"e_1_3_3_1_9_2","unstructured":"Shayan Gharib Konstantinos Drossos Emre Cakir Dmitriy Serdyuk and Tuomas Virtanen. 2018. Unsupervised adversarial domain adaptation for acoustic scene classification. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1808.05777 (2018)."},{"key":"e_1_3_3_1_10_2","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1503.02531 (2015)."},{"key":"e_1_3_3_1_11_2","unstructured":"Ehsan Hosseini-Asl Yingbo Zhou Caiming Xiong and Richard Socher. 2018. Augmented cyclic adversarial learning for low resource domain adaptation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1807.00374 (2018)."},{"key":"e_1_3_3_1_12_2","first-page":"3","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems\u2014Interpretability and Robustness for Audio, Speech and Language Workshop, Montreal, QC, Canada","author":"Hosseini-Asl Ehsan","year":"2018","unstructured":"Ehsan Hosseini-Asl, Yingbo Zhou, Caiming Xiong, and Richard Socher. 2018. Robust domain adaptation by augmented cyclic adversarial learning. In Proceedings of the 31st International Conference on Neural Information Processing Systems\u2014Interpretability and Robustness for Audio, Speech and Language Workshop, Montreal, QC, Canada. 3\u20138."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Wenxin Hou Jindong Wang Xu Tan Tao Qin and Takahiro Shinozaki. 2021. Cross-domain speech recognition with unsupervised character-level distribution matching. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.07491 (2021).","DOI":"10.21437\/Interspeech.2021-57"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.lifelongnlp-1.2"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414299"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925513"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Siddique Latif Rajib Rana Sara Khalifa Raja Jurdak and Bjorn\u00a0Wolfgang Schuller. 2022. Self supervised adversarial domain adaptation for cross-corpus and cross-language speech emotion recognition. IEEE Transactions on Affective Computing (2022).","DOI":"10.1109\/TAFFC.2022.3167013"},{"key":"e_1_3_3_1_18_2","unstructured":"Jinyu Li Michael\u00a0L Seltzer Xi Wang Rui Zhao and Yifan Gong. 2017. Large-scale domain adaptation via teacher-student learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1708.05466 (2017)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462209"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-432"},{"key":"e_1_3_3_1_21_2","unstructured":"Chien-Feng Liao Yu Tsao Hung-Yi Lee and Hsin-Min Wang. 2018. Noise adaptive speech enhancement using domain adversarial training. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1807.07501 (2018)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053074"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268938"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682510"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461682"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683438"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Hyeong-Ju Na and Jeong-Sik Park. 2021. Accented speech recognition based on end-to-end domain adversarial training of neural networks. Applied Sciences 11 18 (2021) 8412.","DOI":"10.3390\/app11188412"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683616"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Sining Sun Binbin Zhang Lei Xie and Yanning Zhang. 2017. An unsupervised deep domain adaptation approach for robust speech recognition. Neurocomputing 257 (2017) 79\u201387.","DOI":"10.1016\/j.neucom.2016.11.063"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462452"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461423"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953163"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418813"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683299"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095177"},{"key":"e_1_3_3_1_37_2","unstructured":"Jiaming Zhou Shiwan Zhao Yaqi Liu Wenjia Zeng Yong Chen and Yong Qin. 2023. kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.13560 (2023)."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Han Zhu Gaofeng Cheng Jindong Wang Wenxin Hou Pengyuan Zhang and Yonghong Yan. 2023. Boosting cross-domain speech recognition with self-supervision. IEEE\/ACM Transactions on Audio Speech and Language Processing (2023).","DOI":"10.1109\/TASLP.2023.3301230"}],"event":{"name":"ICVGIP 2024: Indian Conference on Computer Vision Graphics and Image Processing","acronym":"ICVGIP 2024","location":"Bengaluru Karnataka India"},"container-title":["Proceedings of the Fifteenth Indian Conference on Computer Vision Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702250.3702293","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3702250.3702293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:32Z","timestamp":1750295432000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702250.3702293"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"references-count":37,"alternative-id":["10.1145\/3702250.3702293","10.1145\/3702250"],"URL":"https:\/\/doi.org\/10.1145\/3702250.3702293","relation":{},"subject":[],"published":{"date-parts":[[2024,12,13]]},"assertion":[{"value":"2024-12-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}