{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:05:25Z","timestamp":1765343125455,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62272409"],"award-info":[{"award-number":["No.62272409"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758210","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"12714-12721","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Accent Mandarin Dry-Vocal Singing Dataset: Benchmark for Singing Accent Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5613-3262","authenticated-orcid":false,"given":"Zihao","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China and Carnegie Mellon University, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9908-136X","authenticated-orcid":false,"given":"Shulei","family":"Ji","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China and Innovation Center of Yangtze River Delta, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2266-4209","authenticated-orcid":false,"given":"Le","family":"Ma","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4715-9011","authenticated-orcid":false,"given":"Yuhang","family":"Jin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3597-3913","authenticated-orcid":false,"given":"Shun","family":"Lei","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7690-5570","authenticated-orcid":false,"given":"Jianyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hongkong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8049-013X","authenticated-orcid":false,"given":"Haoying","family":"Fu","sequence":"additional","affiliation":[{"name":"Mei KTV, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1823-9856","authenticated-orcid":false,"given":"Roger B.","family":"Dannenberg","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0778-2303","authenticated-orcid":false,"given":"Kejun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, Zhe Jiang, China and Innovation Center of Yangtze River Delta, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.52462\/jlls.160"},{"key":"e_1_3_2_2_2_1","first-page":"10773","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yu-An Zhou, Jean-Benoit Conneau, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems, Vol. 33 (2020), 10773-10783.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_3_1","volume-title":"YAMNet: A pre-trained model for audio tagging and classification. arXiv preprint arXiv:1710.04860","author":"Bello Alejandro","year":"2017","unstructured":"Alejandro Bello, Jesse Wright, Justin Salamon, Laurent Daudet, and Mark Sandler. 2017. YAMNet: A pre-trained model for audio tagging and classification. arXiv preprint arXiv:1710.04860 (2017)."},{"key":"e_1_3_2_2_4_1","volume-title":"Brian Whitman, and Paul Lamere.","author":"Bertin-Mahieux Thierry","year":"2011","unstructured":"Thierry Bertin-Mahieux, Daniel PW Ellis, Brian Whitman, and Paul Lamere. 2011. The million song dataset. (2011)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Hui Bu Jiayu Du Xingyu Na Bengu Wu and Hao Zheng. 2017. AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline. arXiv:1709.05522 [cs.CL] https:\/\/arxiv.org\/abs\/1709.05522","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"e_1_3_2_2_6_1","volume-title":"Qifusion-Net: Layer-adapted Stream\/Non-stream Model for End-to-End Multi-Accent Speech Recognition. arXiv preprint arXiv:2407.03026","author":"Chen Jinming","year":"2024","unstructured":"Jinming Chen, Jingyi Fang, Yuanzhong Zheng, Yaoxuan Wang, and Haojun Fei. 2024. Qifusion-Net: Layer-adapted Stream\/Non-stream Model for End-to-End Multi-Accent Speech Recognition. arXiv preprint arXiv:2407.03026 (2024)."},{"key":"e_1_3_2_2_7_1","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","volume":"4","author":"Choi Soonbeom","year":"2020","unstructured":"Soonbeom Choi, Wonil Kim, Saebyul Park, Sangeon Yong, and Juhan Nam. 2020. Children's song dataset for singing voice research. In International Society for Music Information Retrieval Conference (ISMIR), Vol. 4."},{"key":"e_1_3_2_2_8_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Copet Jade","year":"2024","unstructured":"Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, and Alexandre D\u00e9fossez. 2024. Simple and controllable music generation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_9_1","first-page":"765","article-title":"SingStyle111: A Multilingual Singing Dataset With Style Transfer","author":"Dai Shuqi","year":"2023","unstructured":"Shuqi Dai, Yuxuan Wu, Siqi Chen, Roy Huang, and Roger B Dannenberg. 2023. SingStyle111: A Multilingual Singing Dataset With Style Transfer.. In ISMIR. 765-773.","journal-title":"ISMIR."},{"key":"e_1_3_2_2_10_1","volume-title":"Alec Radford, and Ilya Sutskever.","author":"Dhariwal Prafulla","year":"2020","unstructured":"Prafulla Dhariwal, Heewoo Jun, Christine Payne, Jong Wook Kim, Alec Radford, and Ilya Sutskever. 2020. Jukebox: A generative model for music. arXiv preprint arXiv:2005.00341 (2020)."},{"key":"e_1_3_2_2_11_1","unstructured":"Zhiyong Zhang Dong Wang Xuewei Zhang. 2015. THCHS-30 : A Free Chinese Speech Corpus. http:\/\/arxiv.org\/abs\/1512.01882"},{"key":"e_1_3_2_2_12_1","volume-title":"Language policy in the People's Republic of China: Theory and practice since","author":"Guo Longsheng","year":"1949","unstructured":"Longsheng Guo. 1949. The relationship between Putonghua and Chinese dialects. In Language policy in the People's Republic of China: Theory and practice since 1949. Springer, 45-54."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414423"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_2_2_15_1","unstructured":"Wei-Nung Hsu Benjamin Tsai Liyang Wang Kuang-Yu Lu Po-Yao Chung Hung-yi Yang Brian Strope Raghav Prabhavalkar Yann Le Yu-Chi Chen et al. 2021. HuBERT: Self-Supervised Learning of Speech Representations by Masked Predictive Coding. arXiv preprint arXiv:2106.07447 (2021)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389671"},{"key":"e_1_3_2_2_18_1","unstructured":"Junya Koguchi and Shinnosuke Takamichi. 2020. PJS: phoneme-balanced Japanese singing voice corpus. arXiv:2006.02959 [cs.SD] https:\/\/arxiv.org\/abs\/2006.02959"},{"key":"e_1_3_2_2_19_1","volume-title":"Lucas Gestin, Wei Zhen Teoh, Jose Sotelo, Alexandre De Brebisson, Yoshua Bengio, and Aaron C Courville.","author":"Kumar Kundan","year":"2019","unstructured":"Kundan Kumar, Rithesh Kumar, Thibault De Boissiere, Lucas Gestin, Wei Zhen Teoh, Jose Sotelo, Alexandre De Brebisson, Yoshua Bengio, and Aaron C Courville. 2019. Melgan: Generative adversarial networks for conditional waveform synthesis. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.01.002"},{"key":"e_1_3_2_2_21_1","first-page":"4158","article-title":"Tone Variations in Regionally Accented Mandarin","author":"Li Yanping","year":"2020","unstructured":"Yanping Li, Catherine T Best, Michael D Tyler, and Denis Burnham. 2020. Tone Variations in Regionally Accented Mandarin.. In INTERSPEECH. 4158-4162.","journal-title":"INTERSPEECH."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1163\/2405478X-00801002"},{"key":"e_1_3_2_2_23_1","volume-title":"Diffsinger: Singing voice synthesis via shallow diffusion mechanism. arXiv preprint arXiv:2105.02446","author":"Liu Jinglin","year":"2021","unstructured":"Jinglin Liu, Chengxi Li, Yi Ren, Feiyang Chen, Peng Liu, and Zhou Zhao. 2021. Diffsinger: Singing voice synthesis via shallow diffusion mechanism. arXiv preprint arXiv:2105.02446, Vol. 2 (2021)."},{"key":"e_1_3_2_2_24_1","volume-title":"Latent Variable Analysis and Signal Separation - 12th International Conference, LVA\/ICA","author":"Liutkus Antoine","year":"2015","unstructured":"Antoine Liutkus, Fabian-Robert St\u00f6ter, Zafar Rafii, Daichi Kitamura, Bertrand Rivet, Nobutaka Ito, Nobutaka Ono, and Julie Fontecave. 2017. The 2016 Signal Separation Evaluation Campaign. In Latent Variable Analysis and Signal Separation - 12th International Conference, LVA\/ICA 2015, Liberec, Czech Republic, August 25-28, 2015, Proceedings, Petr Tichavsk\u00fd, Massoud Babaie-Zadeh, Olivier J.J. Michel, and Nad\u00e8ge Thirion-Moreau (Eds.). Springer International Publishing, Cham, 323-332."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222365"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"e_1_3_2_2_27_1","volume-title":"The Chinese dialects: phonology. The Sino-Tibetan languages","author":"Norman Jerry","year":"2003","unstructured":"Jerry Norman. 2003. The Chinese dialects: phonology. The Sino-Tibetan languages (2003), 72-83."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3332542"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10039"},{"key":"e_1_3_2_2_30_1","volume-title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis. CoRR","author":"Sonobe Ryosuke","year":"2017","unstructured":"Ryosuke Sonobe, Shinnosuke Takamichi, and Hiroshi Saruwatari. 2017. JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis. CoRR, Vol. abs\/1711.00354 (2017). arXiv:1711.00354 http:\/\/arxiv.org\/abs\/1711.00354"},{"key":"e_1_3_2_2_31_1","unstructured":"Hiroki Tamaru Shinnosuke Takamichi Naoko Tanji and Hiroshi Saruwatari. 2020. JVS-MuSiC: Japanese multispeaker singing-voice corpus. arXiv:2001.07044 [cs.SD] https:\/\/arxiv.org\/abs\/2001.07044"},{"key":"e_1_3_2_2_32_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Tang Zhiyuan","year":"2021","unstructured":"Zhiyuan Tang, Dong Wang, Yanguang Xu, Jianwei Sun, Xiaoning Lei, Shuaijiang Zhao, Cheng Wen, Xingjun Tan, Chuandong Xie, Shuran Zhou, et al., 2021. Kespeech: An open source speech dataset of mandarin and its eight subdialects. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_2_33_1","volume-title":"Opencpop: A high-quality open source Chinese popular song corpus for singing voice synthesis. arXiv preprint arXiv:2201.07429","author":"Wang Yu","year":"2022","unstructured":"Yu Wang, Xinsheng Wang, Pengcheng Zhu, Jie Wu, Hanzhao Li, Heyang Xue, Yongmao Zhang, Lei Xie, and Mengxiao Bi. 2022a. Opencpop: A high-quality open source Chinese popular song corpus for singing voice synthesis. arXiv preprint arXiv:2201.07429 (2022)."},{"key":"e_1_3_2_2_34_1","unstructured":"Zihao Wang Shuyu Li Tao Zhang Qi Wang Pengfei Yu Jinyang Luo Yan Liu Ming Xi and Kejun Zhang. 2024a. MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music. arXiv:2402.09871 [cs.SD] https:\/\/arxiv.org\/abs\/2402.09871"},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 7771-7779","author":"Wang Zihao","year":"2024","unstructured":"Zihao Wang, Shuyu Li, Tao Zhang, Qi Wang, Pengfei Yu, Jinyang Luo, Yan Liu, Ming Xi, and Kejun Zhang. 2024b. MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 7771-7779."},{"key":"e_1_3_2_2_36_1","volume-title":"Alignment with Colloquial Expression in Description-to-Song Generation. arXiv preprint arXiv:2407.03188","author":"Wang Zihao","year":"2024","unstructured":"Zihao Wang, Haoxuan Liu, Jiaxing Yu, Tao Zhang, Yan Liu, and Kejun Zhang. 2024c. MuDiT & MuSiT: Alignment with Colloquial Expression in Description-to-Song Generation. arXiv preprint arXiv:2407.03188 (2024)."},{"key":"e_1_3_2_2_37_1","unstructured":"Zihao Wang Le Ma Yongsheng Feng Xin Pan Yuhang Jin and Kejun Zhang. 2024d. SaMoye: Zero-shot Singing Voice Conversion Model Based on Feature Disentanglement and Enhancement. arXiv:2407.07728 [cs.SD] https:\/\/arxiv.org\/abs\/2407.07728"},{"key":"e_1_3_2_2_38_1","unstructured":"Zihao Wang Le Ma Chen Zhang Bo Han Yunfei Xu Yikai Wang Xinyi Chen HaoRong Hong Wenbo Liu Xinda Wu and Kejun Zhang. 2024 e. REMAST: Real-time Emotion-based Music Arrangement with Soft Transition. arXiv:2305.08029 [cs.SD] https:\/\/arxiv.org\/abs\/2305.08029"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3486224"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.360"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548368"},{"key":"e_1_3_2_2_42_1","volume-title":"SongDriver: Real-time Music Accompaniment Generation without Logical Latency nor Exposure Bias. arXiv preprint arXiv:2209.06054","author":"Wang Zihao","year":"2022","unstructured":"Zihao Wang, Kejun Zhang, Yuxing Wang, Chen Zhang, Qihao Liang, Pengfei Yu, Yongsheng Feng, Wenbo Liu, Yikai Wang, Yuntao Bao, and Yiheng Yang. 2022b. SongDriver: Real-time Music Accompaniment Generation without Logical Latency nor Exposure Bias. arXiv preprint arXiv:2209.06054 (2022)."},{"key":"e_1_3_2_2_43_1","volume-title":"MelodyGLM: multi-task pre-training for symbolic melody generation. arXiv preprint arXiv:2309.10738","author":"Wu Xinda","year":"2023","unstructured":"Xinda Wu, Zhijie Huang, Kejun Zhang, Jiaxing Yu, Xu Tan, Tieyao Zhang, Zihao Wang, and Lingyun Sun. 2023. MelodyGLM: multi-task pre-training for symbolic melody generation. arXiv preprint arXiv:2309.10738 (2023)."},{"key":"e_1_3_2_2_44_1","unstructured":"Ruibin Yuan Hanfeng Lin Shawn Guo Ge Zhang Jiahao Pan Yongyi Zang Haohe Liu Xingjian Du Xeron Du Zhen Ye Tianyu Zheng Yinghao Ma Minghao Liu Lijun Yu Zeyue Tian Ziya Zhou Liumeng Xue Xingwei Qu Yizhi Li Tianhao Shen Ziyang Ma Shangda Wu Jun Zhan Chunhui Wang Yatian Wang Xiaohuan Zhou Xiaowei Chi Xinyue Zhang Zhenzhu Yang Yiming Liang Xiangzhou Wang Shansong Liu Lingrui Mei Peng Li Yong Chen Chenghua Lin Xie Chen Gus Xia Zhaoxiang Zhang Chao Zhang Wenhu Chen Xinyu Zhou Xipeng Qiu Roger Dannenberg Jiaheng Liu Jian Yang Stephen Huang Wei Xue Xu Tan and Yike Guo. 2025. YuE: Open Music Foundation Models for Full-Song Generation. https:\/\/github.com\/multimodal-art-projection\/YuE. GitHub repository."},{"key":"e_1_3_2_2_45_1","first-page":"6914","article-title":"M4singer: A multi-style, multi-singer and musical score provided Mandarin singing corpus","volume":"35","author":"Zhang Lichao","year":"2022","unstructured":"Lichao Zhang, Ruiqi Li, Shoutong Wang, Liqun Deng, Jinglin Liu, Yi Ren, Jinzheng He, Rongjie Huang, Jieming Zhu, Xiao Chen, et al., 2022. M4singer: A multi-style, multi-singer and musical score provided Mandarin singing corpus. Advances in Neural Information Processing Systems, Vol. 35 (2022), 6914-6926.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:01:41Z","timestamp":1765342901000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":45,"alternative-id":["10.1145\/3746027.3758210","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758210","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}