{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:46:27Z","timestamp":1765503987978,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761311","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:18:04Z","timestamp":1762561084000},"page":"1979-1988","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ParaStyleTTS: Toward Efficient and Robust Paralinguistic Style Control for Expressive Text-to-Speech Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1359-872X","authenticated-orcid":false,"given":"Haowei","family":"Lou","sequence":"first","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4425-7388","authenticated-orcid":false,"given":"Hye-young","family":"Paik","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4076-1811","authenticated-orcid":false,"given":"Wen","family":"Hu","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4149-839X","authenticated-orcid":false,"given":"Lina","family":"Yao","sequence":"additional","affiliation":[{"name":"CSIRO's Data61, Sydney, NSW, Australia and University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Carnegie Mellon University. 2023. Carnegie Mellon University Pronouncing Dictionary. http:\/\/www.speech.cs.cmu.edu\/cgi-bin\/cmudict'stress=-s&in=CITE Accessed: 2023--12--10."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000155"},{"key":"e_1_3_2_1_3_1","unstructured":"Databaker. 2020. Chinese Mandarin Female Corpus. https:\/\/en.data-baker.com\/datasets\/freeDatasets\/. Accessed: 2023-04--20."},{"key":"e_1_3_2_1_4_1","volume-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens. arXiv preprint arXiv:2407.05407","author":"Du Zhihao","year":"2024","unstructured":"Zhihao Du, Qian Chen, Shiliang Zhang, Kai Hu, Heng Lu, Yexin Yang, Hangrui Hu, Siqi Zheng, Yue Gu, Ziyang Ma, et al. 2024. Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens. arXiv preprint arXiv:2407.05407 (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"e_1_3_2_1_6_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems 27","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, DavidWarde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_7_1","unstructured":"Keith Ito and Linda Johnson. 2017. The LJ Speech Dataset. https:\/\/keithito.com\/LJSpeech-Dataset\/."},{"key":"e_1_3_2_1_8_1","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim Jaehyeon","year":"2020","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--8077.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning. PMLR, 5530--5540","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--5540."},{"key":"e_1_3_2_1_10_1","unstructured":"Diederik P Kingma Max Welling et al. 2013. Auto-encoding variational bayes."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Diederik P Kingma Max Welling et al. 2019. An introduction to variational autoencoders. Foundations and Trends\u00ae in Machine Learning 12 4 (2019) 307--392.","DOI":"10.1561\/2200000056"},{"key":"e_1_3_2_1_12_1","volume-title":"Heli Ben-Hamu, Maximilian Nickel, and Matt Le.","author":"Lipman Yaron","year":"2022","unstructured":"Yaron Lipman, Ricky TQ Chen, Heli Ben-Hamu, Maximilian Nickel, and Matt Le. 2022. Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696409.3700163"},{"key":"e_1_3_2_1_15_1","volume-title":"Generalized Multilingual Text-to-Speech Generation with Language-Aware Style Adaptation. arXiv preprint arXiv:2504.08274","author":"Lou Haowei","year":"2025","unstructured":"Haowei Lou, Hye-young Paik, Sheng Li,Wen Hu, and Lina Yao. 2025. Generalized Multilingual Text-to-Speech Generation with Language-Aware Style Adaptation. arXiv preprint arXiv:2504.08274 (2025)."},{"key":"e_1_3_2_1_16_1","volume-title":"emotion2vec: Self-supervised pre-training for speech emotion representation. arXiv preprint arXiv:2312.15185","author":"Ma Ziyang","year":"2023","unstructured":"Ziyang Ma, Zhisheng Zheng, Jiaxin Ye, Jinchao Li, Zhifu Gao, Shiliang Zhang, and Xie Chen. 2023. emotion2vec: Self-supervised pre-training for speech emotion representation. arXiv preprint arXiv:2312.15185 (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1969.1162058"},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios George","year":"2021","unstructured":"George Papamakarios, Eric Nalisnick, Danilo Jimenez Rezende, Shakir Mohamed, and Balaji Lakshminarayanan. 2021. Normalizing flows for probabilistic modeling and inference. Journal of Machine Learning Research 22, 57 (2021), 1--64.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning. PMLR, 28492--28518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, JongWook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning. PMLR, 28492--28518."},{"key":"e_1_3_2_1_21_1","volume-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech. arXiv preprint arXiv:2006.04558","author":"Ren Yi","year":"2020","unstructured":"Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2020. Fastspeech 2: Fast and high-quality end-to-end text to speech. arXiv preprint arXiv:2006.04558 (2020)."},{"key":"e_1_3_2_1_22_1","volume-title":"Fastspeech: Fast, robust and controllable text to speech. Advances in neural information processing systems 32","author":"Ren Yi","year":"2019","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_2_1_23_1","volume-title":"Mpnet: Masked and permuted pre-training for language understanding. Advances in neural information processing systems 33","author":"Song Kaitao","year":"2020","unstructured":"Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. Mpnet: Masked and permuted pre-training for language understanding. Advances in neural information processing systems 33 (2020), 16857--16867."},{"key":"e_1_3_2_1_24_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"Spark-tts: An efficient llm-based text-to-speech model with single-stream decoupled speech tokens. arXiv preprint arXiv:2503.01710","author":"Wang Xinsheng","year":"2025","unstructured":"Xinsheng Wang, Mingqi Jiang, Ziyang Ma, Ziyu Zhang, Songxiang Liu, Linqin Li, Zheng Liang, Qixi Zheng, Rui Wang, Xiaoqin Feng, et al. 2025. Spark-tts: An efficient llm-based text-to-speech model with single-stream decoupled speech tokens. arXiv preprint arXiv:2503.01710 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135","author":"Skerry-Ryan RJ","year":"2017","unstructured":"YuxuanWang, RJ Skerry-Ryan, Daisy Stanton, YonghuiWu, Ron JWeiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, et al. 2017. Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)."},{"key":"e_1_3_2_1_27_1","volume-title":"A survey on large language model (llm) security and privacy: The good, the bad, and the ugly. High-Confidence Computing","author":"Yao Yifan","year":"2024","unstructured":"Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Zhibo Sun, and Yue Zhang. 2024. A survey on large language model (llm) security and privacy: The good, the bad, and the ugly. High-Confidence Computing (2024), 100211."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:42:10Z","timestamp":1765503730000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761311"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":28,"alternative-id":["10.1145\/3746252.3761311","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761311","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}