{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:14:42Z","timestamp":1765008882218,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","funder":[{"name":"Key Research and Development Program of Shaanxi Province","award":["2024GXYBXM-556"],"award-info":[{"award-number":["2024GXYBXM-556"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3771038","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:08:11Z","timestamp":1765008491000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FabasedVC: Enhancing Voice Conversion with Text Modality Fusion and Phoneme-Level SSL Features"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4849-5035","authenticated-orcid":false,"given":"Wenyu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China and SYKI-SPEECH Team, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1453-0949","authenticated-orcid":false,"given":"Zhetao","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China and SYKI-SPEECH Team, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1453-3820","authenticated-orcid":false,"given":"Yiquan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China; SYKI-SPEECH Team, Xi'an, China and AI Platform Department, bilibili, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2755-1256","authenticated-orcid":false,"given":"Jiacheng","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0075-6380","authenticated-orcid":false,"given":"Zhiyu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2523-9141","authenticated-orcid":false,"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1989-2842","authenticated-orcid":false,"given":"Shihao","family":"Li","sequence":"additional","affiliation":[{"name":"Division of Music and Audio, Union Wheatland Culture and Media Ltd., Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Zal\u00e1n Borsos Rapha\u00ebl Marinier Damien Vincent Eugene Kharitonov Olivier Pietquin Matt Sharifi Dominik Roblek Olivier Teboul David Grangier Marco Tagliasacchi et\u00a0al. 2023. Audiolm: a language modeling approach to audio generation. IEEE\/ACM transactions on audio speech and language processing 31 (2023) 2523\u20132533.","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Sanyuan Chen Chengyi Wang Zhengyang Chen Yu Wu Shujie Liu Zhuo Chen Jinyu Li Naoyuki Kanda Takuya Yoshioka Xiong Xiao et\u00a0al. 2022. Wavlm: Large-scale self-supervised pre-training for full stack speech processing. IEEE Journal of Selected Topics in Signal Processing 16 6 (2022) 1505\u20131518.","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Yiming Cui Wanxiang Che Ting Liu Bing Qin and Ziqing Yang. 2021. Pre-training with whole word masking for chinese bert. IEEE\/ACM Transactions on Audio Speech and Language Processing 29 (2021) 3504\u20133514.","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"e_1_3_3_2_5_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_2_6_2","unstructured":"Zhihao Du Qian Chen Shiliang Zhang Kai Hu Heng Lu Yexin Yang Hangrui Hu Siqi Zheng Yue Gu Ziyang Ma et\u00a0al. 2024. Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.05407 (2024)."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Daniel Erro Antonio Moreno and Antonio Bonafonte. 2010. Voice Conversion Based on Weighted Frequency Warping. IEEE Transactions on Audio Speech and Language Processing 18 5 (2010) 922\u2013931.","DOI":"10.1109\/TASL.2009.2038663"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Zhifu Gao Shiliang Zhang Ian McLoughlin and Zhijie Yan. 2022. Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to-end speech recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2206.08317 (2022).","DOI":"10.21437\/Interspeech.2022-9996"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Wei-Ning Hsu Benjamin Bolte Yao-Hung\u00a0Hubert Tsai Kushal Lakhotia Ruslan Salakhutdinov and Abdelrahman Mohamed. 2021. HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units. IEEE\/ACM Transactions on Audio Speech and Language Processing 29 (2021) 3451\u20133460.","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"e_1_3_3_2_11_2","unstructured":"Jaehyeon Kim Sungwon Kim Jungil Kong and Sungroh Yoon. 2020. Glow-tts: A generative flow for text-to-speech via monotonic alignment search. Advances in Neural Information Processing Systems 33 (2020) 8067\u20138077."},{"key":"e_1_3_3_2_12_2","first-page":"5530","volume-title":"International Conference on Machine Learning","author":"Kim Jaehyeon","year":"2021","unstructured":"Jaehyeon Kim, Jungil Kong, and Juhee Son. 2021. Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In International Conference on Machine Learning. PMLR, 5530\u20135540."},{"key":"e_1_3_3_2_13_2","volume-title":"International Conference on Learning Representations","author":"Kingma Diederik\u00a0P.","year":"2014","unstructured":"Diederik\u00a0P. Kingma and Max Welling. 2014. Auto-encoding variational bayes. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_14_2","unstructured":"Jungil Kong Jaehyeon Kim and Jaekyoung Bae. 2020. Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis. Advances in neural information processing systems 33 (2020) 17022\u201317033."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Jungil Kong Jihoon Park Beomjeong Kim Jeongmin Kim Dohee Kong and Sangjin Kim. 2023. VITS2: Improving quality and efficiency of single-stage text-to-speech with adversarial learning and architecture design. International Speech Communication Association (Interspeech) (2023).","DOI":"10.21437\/Interspeech.2023-534"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-319"},{"key":"e_1_3_3_2_18_2","unstructured":"Songting Liu. 2024. Zero-shot voice conversion with diffusion transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.09943 (2024)."},{"key":"e_1_3_3_2_19_2","first-page":"4721","volume-title":"International Speech Communication Association (Interspeech)","author":"Liu Songxiang","year":"2020","unstructured":"Songxiang Liu, Yuewen Cao, Shiyin Kang, Na Hu, Xunying Liu, Dan Su, Dong Yu, and Helen Meng. 2020. Transferring Source Style in Nonparallel Voice Conversion. In International Speech Communication Association (Interspeech). 4721\u20134725."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"S. Liu Y. Cao D. Wang et\u00a0al. 2021. Any-to-many voice conversion with location-relative sequence-to-sequence modeling. IEEE\/ACM Transactions on Audio Speech and Language Processing 29 (2021) 1717\u20131728.","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"S.\u00a0H. Mohammadi and A. Kain. 2017. An overview of voice conversion systems. Speech Communication 88 (2017) 65\u201382.","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096057"},{"key":"e_1_3_3_2_23_2","unstructured":"Aaron van\u00a0den Oord Sander Dieleman Heiga Zen Karen Simonyan Oriol Vinyals Alex Graves Nal Kalchbrenner Andrew Senior and Koray Kavukcuoglu. 2016. Wavenet: A generative model for raw audio. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1609.03499 (2016)."},{"key":"e_1_3_3_2_24_2","first-page":"18003","volume-title":"International Conference on Machine Learning","author":"Qian Kaizhi","year":"2022","unstructured":"Kaizhi Qian, Yang Zhang, Heting Gao, Junrui Ni, Cheng-I Lai, David Cox, Mark Hasegawa-Johnson, and Shiyu Chang. 2022. Contentvec: An improved self-supervised speech representation by disentangling speakers. In International Conference on Machine Learning. PMLR, 18003\u201318017."},{"key":"e_1_3_3_2_25_2","unstructured":"Yi Ren Yangjun Ruan Xu Tan Tao Qin Sheng Zhao Zhou Zhao and Tie-Yan Liu. 2019. Fastspeech: Fast robust and controllable text to speech. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Yannis Stylianou Olivier Capp\u00e9 and Eric Moulines. 1998. Continuous probabilistic transform for voice conversion. IEEE Transactions on speech and audio processing 6 2 (1998) 131\u2013142.","DOI":"10.1109\/89.661472"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"e_1_3_3_2_30_2","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_3_2_31_2","unstructured":"Chengyi Wang Sanyuan Chen Yu Wu Ziqiang Zhang Long Zhou Shujie Liu Zhuo Chen Yanqing Liu Huaming Wang Jinyu Li et\u00a0al. 2023. Neural codec language models are zero-shot text to speech synthesizers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.02111 (2023)."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Disong Wang Liqun Deng Yu\u00a0Ting Yeung Xiao Chen Xunying Liu and Helen Meng. 2021. Vqmivc: Vector quantization and mutual information-based unsupervised speech representation disentanglement for one-shot voice conversion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.10132 (2021).","DOI":"10.21437\/Interspeech.2021-283"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Yuxuan Wang RJ Skerry-Ryan Daisy Stanton Yonghui Wu Ron\u00a0J Weiss Navdeep Jaitly Zongheng Yang Ying Xiao Zhifeng Chen Samy Bengio et\u00a0al. 2017. Tacotron: Towards End-to-End Speech Synthesis. Interspeech 2017 (2017) 4006.","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1351"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054337"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Yongmao Zhang Heyang Xue Hanzhao Li Lei Xie Tingwei Guo Ruixiong Zhang and Caixia Gong. 2022. Visinger 2: High-fidelity end-to-end singing voice synthesis enhanced by digital signal processing synthesizer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.02903 (2022).","DOI":"10.21437\/Interspeech.2023-391"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Ya-Jie Zhang and Zhen-Hua Ling. 2021. Extracting and predicting word-level style variations for speech synthesis. IEEE\/ACM Transactions on Audio Speech and Language Processing 29 (2021) 1582\u20131593.","DOI":"10.1109\/TASLP.2021.3074757"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747625"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00291"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3771038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:11:25Z","timestamp":1765008685000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3771038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":38,"alternative-id":["10.1145\/3743093.3771038","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3771038","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}