{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:34:24Z","timestamp":1776890064122,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"name":"the National Natural Science Foundation of China","award":["No. U23B2018 and No. 62206171"],"award-info":[{"award-number":["No. U23B2018 and No. 62206171"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754829","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"10748-10757","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3614-1346","authenticated-orcid":false,"given":"Guanrou","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7972-5457","authenticated-orcid":false,"given":"Chen","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6939-7438","authenticated-orcid":false,"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Tongyi Speech Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8195-3262","authenticated-orcid":false,"given":"Ziyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8303-930X","authenticated-orcid":false,"given":"Wenxi","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0356-1968","authenticated-orcid":false,"given":"Wen","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongyi Speech Lab, Sunnyvale, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2765-5889","authenticated-orcid":false,"given":"Tianrui","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0588-1812","authenticated-orcid":false,"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1880-7434","authenticated-orcid":false,"given":"Zhikang","family":"Niu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5940-5369","authenticated-orcid":false,"given":"Wenrui","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5958-1131","authenticated-orcid":false,"given":"Fan","family":"Yu","sequence":"additional","affiliation":[{"name":"Tongyi Speech Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3509-9322","authenticated-orcid":false,"given":"Zhihao","family":"Du","sequence":"additional","affiliation":[{"name":"Tongyi Speech Lab, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5691-7324","authenticated-orcid":false,"given":"Zhifu","family":"Gao","sequence":"additional","affiliation":[{"name":"Tongyi Speech Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1718-3686","authenticated-orcid":false,"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongyi Speech Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7423-617X","authenticated-orcid":false,"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai Innovation Institute, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Philip Anastassiou Jiawei Chen Jitong Chen et al. 2024. Seed-TTS: A Family of High-Quality Versatile Speech Generation Models."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"e_1_3_2_1_3_1","volume-title":"Controlling emotion in text-to-speech with natural language prompts. arXiv preprint","author":"Bott Thomas","year":"2024","unstructured":"Thomas Bott, Florian Lux, and Ngoc Thang Vu. 2024. Controlling emotion in text-to-speech with natural language prompts. arXiv preprint (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Wenxi Chen Ziyang Ma Ruiqi Yan Yuzhe Liang Xiquan Li Ruiyang Xu Zhikang Niu Yanqiao Zhu Yifan Yang Zhanxun Liu et al. 2024. SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training. arXiv preprint (2024).","DOI":"10.18653\/v1\/2025.findings-acl.115"},{"key":"e_1_3_2_1_5_1","volume-title":"EmoSphere-TTS: Emotional style and intensity modeling via spherical emotion vector for controllable emotional text-to-speech. arXiv preprint","author":"Cho Deok-Hyeon","year":"2024","unstructured":"Deok-Hyeon Cho, Hyung-Seok Oh, Seung-Bin Kim, Sang-Hoon Lee, and Seong-Whan Lee. 2024b. EmoSphere-TTS: Emotional style and intensity modeling via spherical emotion vector for controllable emotional text-to-speech. arXiv preprint (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"EmoSphere: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector. arXiv preprint","author":"Cho Deok-Hyeon","year":"2024","unstructured":"Deok-Hyeon Cho, Hyung-Seok Oh, Seung-Bin Kim, and Seong-Whan Lee. 2024a. EmoSphere: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector. arXiv preprint (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Emospeech: Guiding fastspeech2 towards emotional text to speech. arXiv preprint","author":"Diatlova Daria","year":"2023","unstructured":"Daria Diatlova and Vitaly Shutov. 2023. Emospeech: Guiding fastspeech2 towards emotional text to speech. arXiv preprint (2023)."},{"key":"e_1_3_2_1_8_1","unstructured":"Zhihao Du Qian Chen Shiliang Zhang et al. 2024a. CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens. arXiv:2407.05407 [cs.CL]"},{"key":"e_1_3_2_1_9_1","unstructured":"Zhihao Du Yuxuan Wang Qian Chen et al. 2024b. CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models. arXiv:2412.10117 [cs.CL]"},{"key":"e_1_3_2_1_10_1","volume-title":"Llama-omni: Seamless speech interaction with large language models. arXiv preprint","author":"Fang Qingkai","year":"2024","unstructured":"Qingkai Fang, Shoutao Guo, Yan Zhou, Zhengrui Ma, Shaolei Zhang, and Yang Feng. 2024. Llama-omni: Seamless speech interaction with large language models. arXiv preprint (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"LUCY: Linguistic Understanding and Control Yielding Early Stage of Her. arXiv preprint","author":"Gao Heting","year":"2025","unstructured":"Heting Gao, Hang Shao, Xiong Wang, Chaofan Qiu, Yunhang Shen, Siqi Cai, Yuchen Shi, Zihan Xu, Zuwei Long, Yike Zhang, et al., 2025. LUCY: Linguistic Understanding and Control Yielding Early Stage of Her. arXiv preprint (2025)."},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. ICASSP.","author":"Gao Xiaoxue","unstructured":"Xiaoxue Gao, Chen Zhang, Yiming Chen, Huayun Zhang, and Nancy F Chen. [n.d.]. Emo-dpo: Controllable emotional speech synthesis through direct preference optimization. In Proc. ICASSP."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095621"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890588"},{"key":"e_1_3_2_1_16_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"Subrata Biswas, and Bashima Islam.","author":"Imran Sheikh Asif","year":"2024","unstructured":"Sheikh Asif Imran, Mohammad Nur Hossain Khan, Subrata Biswas, and Bashima Islam. 2024. LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors. arXiv preprint (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445879"},{"key":"e_1_3_2_1_19_1","volume-title":"Controlspeech: Towards simultaneous zero-shot speaker cloning and zero-shot language style control with decoupled codec. arXiv preprint","author":"Ji Shengpeng","year":"2024","unstructured":"Shengpeng Ji, Jialong Zuo, Wen Wang, Minghui Fang, Siqi Zheng, Qian Chen, Ziyue Jiang, Hai Huang, Zehan Wang, Xize Cheng, et al., 2024b. Controlspeech: Towards simultaneous zero-shot speaker cloning and zero-shot language style control with decoupled codec. arXiv preprint (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"Exploring the impact of instruction data scaling on large language models: An empirical study on real-world use cases. arXiv preprint","author":"Ji Yunjie","year":"2023","unstructured":"Yunjie Ji, Yong Deng, Yan Gong, Yiping Peng, Qiang Niu, Lei Zhang, Baochang Ma, and Xiangang Li. 2023. Exploring the impact of instruction data scaling on large language models: An empirical study on real-world use cases. arXiv preprint (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Sung Ju Hwang, and Eunho Yang","author":"Kang Minki","year":"2023","unstructured":"Minki Kang, Wooseok Han, Sung Ju Hwang, and Eunho Yang. 2023. ZET-Speech: Zero-shot adaptive emotion-controllable text-to-speech synthesis with diffusion and style-based models. arXiv preprint (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Proc. NeurIPS. Virtual.","author":"Kong Jungil","year":"2020","unstructured":"Jungil Kong, Jaehyeon Kim, and Jaekyoung Bae. 2020. HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis. In Proc. NeurIPS. Virtual."},{"key":"e_1_3_2_1_23_1","unstructured":"Yichong Leng Zhifang Guo Kai Shen Xu Tan Zeqian Ju Yanqing Liu Yufei Liu Dongchao Yang Leying Zhang Kaitao Song et al. 2023. Prompttts 2: Describing and generating voices with text prompt. arXiv preprint (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Promptstyle: Controllable style transfer for text-to-speech with natural language descriptions. arXiv preprint","author":"Liu Guanghou","year":"2023","unstructured":"Guanghou Liu, Yongmao Zhang, Yi Lei, Yunlin Chen, Rui Wang, Zhifei Li, and Lei Xie. 2023b. Promptstyle: Controllable style transfer for text-to-speech with natural language descriptions. arXiv preprint (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Vit-tts: visual text-to-speech with scalable diffusion transformer. arXiv preprint arXiv:2305.12708","author":"Liu Huadai","year":"2023","unstructured":"Huadai Liu, Rongjie Huang, Xuan Lin, Wenqiang Xu, Maozong Zheng, Hong Chen, Jinzheng He, and Zhou Zhao. 2023a. Vit-tts: visual text-to-speech with scalable diffusion transformer. arXiv preprint arXiv:2305.12708 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Medic: Zero-shot music editing with disentangled inversion control. arXiv preprint","author":"Liu Huadai","year":"2024","unstructured":"Huadai Liu, Jialei Wang, Xiangtai Li, Rongjie Huang, Yang Liu, Jiayang Xu, and Zhou Zhao. 2024. Medic: Zero-shot music editing with disentangled inversion control. arXiv preprint (2024)."},{"key":"e_1_3_2_1_27_1","unstructured":"Wenrui Liu Qian Chen Wen Wang Yafeng Chen Jin Xu Zhifang Guo Guanrou Yang Weiqin Li Xiaoda Yang Tao Jin et al. 2025. Speech Token Prediction via Compressed-to-fine Language Modeling for Speech Generation. arXiv preprint (2025)."},{"key":"e_1_3_2_1_28_1","volume-title":"Proc. ICLR.","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In Proc. ICLR."},{"key":"e_1_3_2_1_29_1","volume-title":"Emobox: Multilingual multi-corpus speech emotion recognition toolkit and benchmark. arXiv preprint","author":"Ma Ziyang","year":"2024","unstructured":"Ziyang Ma, Mingjie Chen, Hezhao Zhang, Zhisheng Zheng, Wenxi Chen, Xiquan Li, Jiaxin Ye, Xie Chen, and Thomas Hain. 2024. Emobox: Multilingual multi-corpus speech emotion recognition toolkit and benchmark. arXiv preprint (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"emotion2vec: Self-supervised pre-training for speech emotion representation. arXiv preprint","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 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. ICML. Honolulu.","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, et al., 2023. Robust speech recognition via large-scale weak supervision. In Proc. ICML. Honolulu."},{"key":"e_1_3_2_1_32_1","volume-title":"Proc. ICLR. Virtual.","author":"Ren Yi","year":"2021","unstructured":"Yi Ren, Chenxu Hu, Xu Tan, et al., 2021. FastSpeech 2: Fast and High-Quality End-to-End Text to Speech. In Proc. ICLR. Virtual."},{"key":"e_1_3_2_1_33_1","volume-title":"Utmos: Utokyo-sarulab system for voicemos challenge","author":"Saeki Takaaki","year":"2022","unstructured":"Takaaki Saeki, Detai Xin, Wataru Nakata, Tomoki Koriyama, Shinnosuke Takamichi, and Hiroshi Saruwatari. 2022. Utmos: Utokyo-sarulab system for voicemos challenge 2022. arXiv preprint (2022)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890141"},{"key":"e_1_3_2_1_35_1","volume-title":"OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents. arXiv preprint","author":"Sun Qiang","year":"2024","unstructured":"Qiang Sun, Yuanyi Luo, Sirui Li, Wenxiao Zhang, and Wei Liu. 2024. OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents. arXiv preprint (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446467"},{"key":"e_1_3_2_1_37_1","volume-title":"Emomix: Emotion mixing via diffusion models for emotional speech synthesis. arXiv preprint","author":"Tang Haobin","year":"2023","unstructured":"Haobin Tang, Xulong Zhang, Jianzong Wang, Ning Cheng, and Jing Xiao. 2023a. Emomix: Emotion mixing via diffusion models for emotional speech synthesis. arXiv preprint (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095623"},{"key":"e_1_3_2_1_39_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint (2023)."},{"key":"e_1_3_2_1_40_1","unstructured":"Chengyi Wang Sanyuan Chen Yu Wu et al. 2023a. Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers. arXiv:2301.02111 [cs.CL]"},{"key":"e_1_3_2_1_41_1","volume-title":"EmoPro: A Prompt Selection Strategy for Emotional Expression in LM-based Speech Synthesis. arXiv preprint","author":"Wang Haoyu","year":"2024","unstructured":"Haoyu Wang, Chunyu Qiang, Tianrui Wang, Cheng Gong, Qiuyu Liu, Yu Jiang, Xiaobao Wang, Chenyang Wang, and Chen Zhang. 2024b. EmoPro: A Prompt Selection Strategy for Emotional Expression in LM-based Speech Synthesis. arXiv preprint (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097118"},{"key":"e_1_3_2_1_43_1","volume-title":"Spark-tts: An efficient llm-based text-to-speech model with single-stream decoupled speech tokens. arXiv preprint","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 (2025)."},{"key":"e_1_3_2_1_44_1","volume-title":"Freeze-omni: A smart and low latency speech-to-speech dialogue model with frozen llm. arXiv preprint","author":"Wang Xiong","year":"2024","unstructured":"Xiong Wang, Yangze Li, Chaoyou Fu, Yunhang Shen, Lei Xie, Ke Li, Xing Sun, and Long Ma. 2024a. Freeze-omni: A smart and low latency speech-to-speech dialogue model with frozen llm. arXiv preprint (2024)."},{"key":"e_1_3_2_1_45_1","volume-title":"Proc. NeurIPS","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Proc. NeurIPS (2022)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832181"},{"key":"e_1_3_2_1_47_1","volume-title":"Mini-omni: Language models can hear, talk while thinking in streaming. arXiv preprint","author":"Xie Zhifei","year":"2024","unstructured":"Zhifei Xie and Changqiao Wu. 2024a. Mini-omni: Language models can hear, talk while thinking in streaming. arXiv preprint (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"Mini-omni2: Towards open-source gpt-4o with vision, speech and duplex capabilities. arXiv preprint","author":"Xie Zhifei","year":"2024","unstructured":"Zhifei Xie and Changqiao Wu. 2024b. Mini-omni2: Towards open-source gpt-4o with vision, speech and duplex capabilities. arXiv preprint (2024)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29902"},{"key":"e_1_3_2_1_50_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024c. Qwen2. 5 technical report. arXiv preprint (2024)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"e_1_3_2_1_52_1","unstructured":"Yifan Yang Ziyang Ma Shujie Liu Jinyu Li Hui Wang Lingwei Meng Haiyang Sun Yuzhe Liang Ruiyang Xu Yuxuan Hu et al. 2024b. Interleaved Speech-Text Language Models are Simple Streaming Text to Speech Synthesizers. arXiv preprint (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Speechgpt: Empowering large language models with intrinsic cross-modal conversational abilities. arXiv preprint","author":"Zhang Dong","year":"2023","unstructured":"Dong Zhang, Shimin Li, Xin Zhang, Jun Zhan, Pengyu Wang, Yaqian Zhou, and Xipeng Qiu. 2023. Speechgpt: Empowering large language models with intrinsic cross-modal conversational abilities. arXiv preprint (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al., 2022. Opt: Open pre-trained transformer language models. arXiv preprint (2022)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:45:54Z","timestamp":1765309554000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754829"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":54,"alternative-id":["10.1145\/3746027.3754829","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754829","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"}}]}}