{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:10:04Z","timestamp":1756487404846,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T00:00:00Z","timestamp":1706227200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Zhejiang Electric Power Co., Ltd.","award":["Science and Technology Project No.B311YF230001"],"award-info":[{"award-number":["Science and Technology Project No.B311YF230001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,26]]},"DOI":"10.1145\/3640824.3640861","type":"proceedings-article","created":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T12:05:28Z","timestamp":1709899528000},"page":"232-237","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Accent Similarity for Cross-Accented Speech Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8179-1829","authenticated-orcid":false,"given":"Hongjie","family":"Gu","sequence":"first","affiliation":[{"name":"Marketing Service Center, State Grid Zhejiang Electric Power Co., Ltd, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0219-6975","authenticated-orcid":false,"given":"Gang","family":"Sun","sequence":"additional","affiliation":[{"name":"Marketing Service Center, State Grid Zhejiang Electric Power Co., Ltd, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6851-6931","authenticated-orcid":false,"given":"Ran","family":"Shen","sequence":"additional","affiliation":[{"name":"Marketing Service Center, State Grid Zhejiang Electric Power Co., Ltd, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2531-2213","authenticated-orcid":false,"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Marketing Service Center, State Grid Zhejiang Electric Power Co., Ltd, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8093-4437","authenticated-orcid":false,"given":"Weihao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2663-0848","authenticated-orcid":false,"given":"Junjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,3,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Accented speech recognition: Benchmarking, pre-training, and diverse data. arXiv preprint arXiv:2205.08014","author":"Aks\u00ebnova Al\u00ebna","year":"2022","unstructured":"Al\u00ebna Aks\u00ebnova, Zhehuai Chen, Chung-Cheng Chiu, Daan van Esch, Pavel Golik, Wei Han, Levi King, Bhuvana Ramabhadran, Andrew Rosenberg, Suzan Schwartz, 2022. Accented speech recognition: Benchmarking, pre-training, and diverse data. arXiv preprint arXiv:2205.08014 (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"Common voice: A massively-multilingual speech corpus. arXiv preprint arXiv:1912.06670","author":"Ardila Rosana","year":"2019","unstructured":"Rosana Ardila, Megan Branson, Kelly Davis, Michael Henretty, Michael Kohler, Josh Meyer, Reuben Morais, Lindsay Saunders, Francis\u00a0M Tyers, and Gregor Weber. 2019. Common voice: A massively-multilingual speech corpus. arXiv preprint arXiv:1912.06670 (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053098"},{"key":"e_1_3_2_1_4_1","volume-title":"International conference on machine learning. PMLR, 1126\u20131135","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning. PMLR, 1126\u20131135."},{"key":"e_1_3_2_1_5_1","volume-title":"Meta-learning for low-resource neural machine translation. arXiv preprint arXiv:1808.08437","author":"Gu Jiatao","year":"2018","unstructured":"Jiatao Gu, Yong Wang, Yun Chen, Kyunghyun Cho, and Victor\u00a0OK Li. 2018. Meta-learning for low-resource neural machine translation. arXiv preprint arXiv:1808.08437 (2018)."},{"key":"e_1_3_2_1_6_1","volume-title":"Supervised contrastive learning for accented speech recognition. arXiv preprint arXiv:2107.00921","author":"Han Tao","year":"2021","unstructured":"Tao Han, Hantao Huang, Ziang Yang, and Wei Han. 2021. Supervised contrastive learning for accented speech recognition. arXiv preprint arXiv:2107.00921 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"Accented speech recognition: A survey. arXiv preprint arXiv:2104.10747","author":"Hinsvark Arthur","year":"2021","unstructured":"Arthur Hinsvark, Natalie Delworth, Miguel Del\u00a0Rio, Quinten McNamara, Joshua Dong, Ryan Westerman, Michelle Huang, Joseph Palakapilly, Jennifer Drexler, Ilya Pirkin, 2021. Accented speech recognition: A survey. arXiv preprint arXiv:2104.10747 (2021)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414959"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053112"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414291"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Abhinav Jain Minali Upreti and Preethi Jyothi. 2018. Improved Accented Speech Recognition Using Accent Embeddings and Multi-task Learning.. In Interspeech. 2454\u20132458.","DOI":"10.21437\/Interspeech.2018-1864"},{"key":"e_1_3_2_1_13_1","volume-title":"Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. arXiv preprint arXiv:1808.06226","author":"Kudo Taku","year":"2018","unstructured":"Taku Kudo and John Richardson. 2018. Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. arXiv preprint arXiv:1808.06226 (2018)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"e_1_3_2_1_15_1","volume-title":"Accent-robust automatic speech recognition using supervised and unsupervised wav2vec embeddings. arXiv preprint arXiv:2110.03520","author":"Li Jialu","year":"2021","unstructured":"Jialu Li, Vimal Manohar, Pooja Chitkara, Andros Tjandra, Michael Picheny, Frank Zhang, Xiaohui Zhang, and Yatharth Saraf. 2021. Accent-robust automatic speech recognition using supervised and unsupervised wav2vec embeddings. arXiv preprint arXiv:2110.03520 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3198546"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462663"},{"key":"e_1_3_2_1_19_1","volume-title":"Residual adapters for parameter-efficient ASR adaptation to atypical and accented speech. arXiv preprint arXiv:2109.06952","author":"Tomanek Katrin","year":"2021","unstructured":"Katrin Tomanek, Vicky Zayats, Dirk Padfield, Kara Vaillancourt, and Fadi Biadsy. 2021. Residual adapters for parameter-efficient ASR adaptation to atypical and accented speech. arXiv preprint arXiv:2109.06952 (2021)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268945"},{"key":"e_1_3_2_1_21_1","volume-title":"Learning fast adaptation on cross-accented speech recognition. arXiv preprint arXiv:2003.01901","author":"Winata Genta\u00a0Indra","year":"2020","unstructured":"Genta\u00a0Indra Winata, Samuel Cahyawijaya, Zihan Liu, Zhaojiang Lin, Andrea Madotto, Peng Xu, and Pascale Fung. 2020. Learning fast adaptation on cross-accented speech recognition. arXiv preprint arXiv:2003.01901 (2020)."},{"key":"e_1_3_2_1_22_1","volume-title":"E2E-based multi-task learning approach to joint speech and accent recognition. arXiv preprint arXiv:2106.08211","author":"Zhang Jicheng","year":"2021","unstructured":"Jicheng Zhang, Yizhou Peng, Pham Van\u00a0Tung, Haihua Xu, Hao Huang, and Eng\u00a0Siong Chng. 2021. E2E-based multi-task learning approach to joint speech and accent recognition. arXiv preprint arXiv:2106.08211 (2021)."}],"event":{"name":"CCEAI 2024: 2024 8th International Conference on Control Engineering and Artificial Intelligence","acronym":"CCEAI 2024","location":"Shanghai China"},"container-title":["2024 8th International Conference on Control Engineering and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640824.3640861","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640824.3640861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T16:45:53Z","timestamp":1756485953000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640824.3640861"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,26]]},"references-count":22,"alternative-id":["10.1145\/3640824.3640861","10.1145\/3640824"],"URL":"https:\/\/doi.org\/10.1145\/3640824.3640861","relation":{},"subject":[],"published":{"date-parts":[[2024,1,26]]},"assertion":[{"value":"2024-03-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}