{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:05:10Z","timestamp":1784268310462,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","funder":[{"name":"the National Natural Science Foundation of China","award":["62471420"],"award-info":[{"award-number":["62471420"]}]},{"name":"GuangDong Basic and Applied Basic Research Foundation","award":["2025A1515012296"],"award-info":[{"award-number":["2025A1515012296"]}]},{"name":"CCF-Tencent Rhino-Bird Open Research Fund"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755758","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"8872-8881","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0857-203X","authenticated-orcid":false,"given":"Yan","family":"Rong","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2614-2598","authenticated-orcid":false,"given":"Jinting","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Technology and Science (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6136-7619","authenticated-orcid":false,"given":"Guangzhi","family":"Lei","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4464-146X","authenticated-orcid":false,"given":"Shan","family":"Yang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4497-0135","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_2_1","first-page":"1","article-title":"Video generation models as world simulators","volume":"1","author":"Brooks Tim","year":"2024","unstructured":"Tim Brooks, Bill Peebles, Connor Holmes, Will DePue, Yufei Guo, Li Jing, David Schnurr, Joe Taylor, Troy Luhman, Eric Luhman, et al., 2024. Video generation models as world simulators. OpenAI Blog, Vol. 1, 8 (2024), 1.","journal-title":"OpenAI Blog"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 22-30","author":"Chen Guangyao","year":"2024","unstructured":"Guangyao Chen, Siwei Dong, Yu Shu, Ge Zhang, Jaward Sesay, B\u00f6rje Karlsson, Jie Fu, and Yemin Shi. 2024a. AutoAgents: a framework for automatic agent generation. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 22-30."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"e_1_3_2_1_5_1","volume-title":"F5-tts: A fairytaler that fakes fluent and faithful speech with flow matching. arXiv preprint arXiv:2410.06885","author":"Chen Yushen","year":"2024","unstructured":"Yushen Chen, Zhikang Niu, Ziyang Ma, Keqi Deng, Chunhui Wang, Jian Zhao, Kai Yu, and Xie Chen. 2024b. F5-tts: A fairytaler that fakes fluent and faithful speech with flow matching. arXiv preprint arXiv:2410.06885 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Taming multimodal joint training for high-quality video-to-audio synthesis. arXiv preprint arXiv:2412.15322","author":"Cheng Ho Kei","year":"2024","unstructured":"Ho Kei Cheng, Masato Ishii, Akio Hayakawa, Takashi Shibuya, Alexander Schwing, and Yuki Mitsufuji. 2024. Taming multimodal joint training for high-quality video-to-audio synthesis. arXiv preprint arXiv:2412.15322 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889780"},{"key":"e_1_3_2_1_8_1","volume-title":"Syncfusion: Multimodal Onset-Synchronized Video-to-Audio Foley Synthesis. In IEEE International Conference on Acoustics, Speech and Signal Processing. 936-940","author":"Comunit\u00e0 Marco","year":"2024","unstructured":"Marco Comunit\u00e0, Riccardo F Gramaccioni, Emilian Postolache, Emanuele Rodol\u00e0, Danilo Comminiello, and Joshua D Reiss. 2024. Syncfusion: Multimodal Onset-Synchronized Video-to-Audio Foley Synthesis. In IEEE International Conference on Acoustics, Speech and Signal Processing. 936-940."},{"key":"e_1_3_2_1_9_1","first-page":"6767","article-title":"StyleDubber","author":"Cong Gaoxiang","year":"2024","unstructured":"Gaoxiang Cong, Yuankai Qi, Liang Li, Amin Beheshti, Zhedong Zhang, Anton Hengel, Ming-Hsuan Yang, Chenggang Yan, and Qingming Huang. 2024. StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing. In Findings of the Association for Computational Linguistics. 6767-6779.","journal-title":"Towards Multi-Scale Style Learning for Movie Dubbing. In Findings of the Association for Computational Linguistics."},{"key":"e_1_3_2_1_10_1","first-page":"47704","article-title":"Simple and controllable music generation","volume":"36","author":"Copet Jade","year":"2023","unstructured":"Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, and Alexandre D\u00e9fossez. 2023. Simple and controllable music generation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 47704-47720.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","volume-title":"ICML Workshop on Foundation Models in the Wild.","author":"Dagli Rishit","year":"2024","unstructured":"Rishit Dagli, Shivesh Prakash, Robert Wu, and Houman Khosravani. 2024. SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound. In ICML Workshop on Foundation Models in the Wild."},{"key":"e_1_3_2_1_12_1","first-page":"3320","article-title":"PAM","author":"Deshmukh Soham","year":"2024","unstructured":"Soham Deshmukh, Dareen Alharthi, Benjamin Elizalde, Hannes Gamper, Mahmoud Al Ismail, Rita Singh, Bhiksha Raj, and Huaming Wang. 2024. PAM: Prompting Audio-Language Models for Audio Quality Assessment. In Proc. Interspeech. 3320-3324.","journal-title":"Prompting Audio-Language Models for Audio Quality Assessment. In Proc. Interspeech."},{"key":"e_1_3_2_1_13_1","volume-title":"Songcomposer: A large language model for lyric and melody composition in song generation. arXiv preprint arXiv:2402.17645","author":"Ding Shuangrui","year":"2024","unstructured":"Shuangrui Ding, Zihan Liu, Xiaoyi Dong, Pan Zhang, Rui Qian, Conghui He, Dahua Lin, and Jiaqi Wang. 2024. Songcomposer: A large language model for lyric and melody composition in song generation. arXiv preprint arXiv:2402.17645 (2024)."},{"key":"e_1_3_2_1_14_1","unstructured":"Zhihao Du Yuxuan Wang Qian Chen Xian Shi Xiang Lv Tianyu Zhao Zhifu Gao Yexin Yang Changfeng Gao Hui Wang et al. 2024. Cosyvoice 2: Scalable streaming speech synthesis with large language models. arXiv preprint arXiv:2412.10117 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1067343.1067361"},{"key":"e_1_3_2_1_16_1","volume-title":"Fireredtts: A foundation text-to-speech framework for industry-level generative speech applications. arXiv preprint arXiv:2409.03283","author":"Guo Hao-Han","year":"2024","unstructured":"Hao-Han Guo, Kun Liu, Fei-Yu Shen, Yi-Chen Wu, Feng-Long Xie, Kun Xie, and Kai-Tuo Xu. 2024a. Fireredtts: A foundation text-to-speech framework for industry-level generative speech applications. arXiv preprint arXiv:2409.03283 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Gotta hear them all: Sound source aware vision to audio generation. arXiv preprint arXiv:2411.15447","author":"Guo Wei","year":"2024","unstructured":"Wei Guo, Heng Wang, Jianbo Ma, and Weidong Cai. 2024b. Gotta hear them all: Sound source aware vision to audio generation. arXiv preprint arXiv:2411.15447 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Richard He Bai, Zakaria Aldeneh, and Navdeep Jaitly.","author":"Gupta Akshita","year":"2024","unstructured":"Akshita Gupta, Tatiana Likhomanenko, Karren Dai Yang, Richard He Bai, Zakaria Aldeneh, and Navdeep Jaitly. 2024. Visatronic: A Multimodal Decoder-Only Model for Speech Synthesis. arXiv preprint arXiv:2411.17690 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment. arXiv preprint arXiv:2404.09313","author":"Hong Zhiqing","year":"2024","unstructured":"Zhiqing Hong, Rongjie Huang, Xize Cheng, Yongqi Wang, Ruiqi Li, Fuming You, Zhou Zhao, and Zhimeng Zhang. 2024. Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment. arXiv preprint arXiv:2404.09313 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning. 13916-13932","author":"Huang Rongjie","year":"2023","unstructured":"Rongjie Huang, Jiawei Huang, Dongchao Yang, Yi Ren, Luping Liu, Mingze Li, Zhenhui Ye, Jinglin Liu, Xiang Yin, and Zhou Zhao. 2023. Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models. In International Conference on Machine Learning. 13916-13932."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"e_1_3_2_1_22_1","volume-title":"From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech. arXiv preprint arXiv:2503.16956","author":"Kim Ji-Hoon","year":"2025","unstructured":"Ji-Hoon Kim, Jeongsoo Choi, Jaehun Kim, Chaeyoung Jung, and Joon Son Chung. 2025. From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech. arXiv preprint arXiv:2503.16956 (2025)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.543"},{"key":"e_1_3_2_1_24_1","first-page":"80107","article-title":"Songcreator: Lyrics-based universal song generation","volume":"37","author":"Lei Shun","year":"2024","unstructured":"Shun Lei, Yixuan Zhou, Boshi Tang, Max WY Lam, Hangyu Liu, Jingcheng Wu, Shiyin Kang, Zhiyong Wu, Helen Meng, et al., 2024b. Songcreator: Lyrics-based universal song generation. Advances in Neural Information Processing Systems, Vol. 37 (2024), 80107-80140.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization. arXiv preprint arXiv:2410.12957","author":"Li Ruiqi","year":"2024","unstructured":"Ruiqi Li, Siqi Zheng, Xize Cheng, Ziang Zhang, Shengpeng Ji, and Zhou Zhao. 2024b. MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization. arXiv preprint arXiv:2410.12957 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687688"},{"key":"e_1_3_2_1_27_1","volume-title":"ICLR Workshop on LLM Agents.","author":"Liang Jinhua","year":"2024","unstructured":"Jinhua Liang, Huan Zhang, Haohe Liu, Yin Cao, Qiuqiang Kong, Xubo Liu, Wenwu Wang, Mark D Plumbley, Huy Phan, and Emmanouil Benetos. 2024. Wavcraft: Audio editing and generation with natural language prompts. ICLR Workshop on LLM Agents."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447246"},{"key":"e_1_3_2_1_29_1","volume-title":"Audioldm: Text-to-audio generation with latent diffusion models. arXiv preprint arXiv:2301.12503","author":"Liu Haohe","year":"2023","unstructured":"Haohe Liu, Zehua Chen, Yi Yuan, Xinhao Mei, Xubo Liu, Danilo Mandic, Wenwu Wang, and Mark D Plumbley. 2023. Audioldm: Text-to-audio generation with latent diffusion models. arXiv preprint arXiv:2301.12503 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447027"},{"key":"e_1_3_2_1_31_1","volume-title":"Separate anything you describe","author":"Liu Xubo","year":"2024","unstructured":"Xubo Liu, Qiuqiang Kong, Yan Zhao, Haohe Liu, Yi Yuan, Yuzhuo Liu, Rui Xia, Yuxuan Wang, Mark D Plumbley, and Wenwu Wang. 2024c. Separate anything you describe. IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation. arXiv preprint arXiv:2502.13128","author":"Liu Zihan","year":"2025","unstructured":"Zihan Liu, Shuangrui Ding, Zhixiong Zhang, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Dahua Lin, and Jiaqi Wang. 2025. SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation. arXiv preprint arXiv:2502.13128 (2025)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"e_1_3_2_1_34_1","volume-title":"Mustango: Toward controllable text-to-music generation. arXiv preprint arXiv:2311.08355","author":"Melechovsky Jan","year":"2023","unstructured":"Jan Melechovsky, Zixun Guo, Deepanway Ghosal, Navonil Majumder, Dorien Herremans, and Soujanya Poria. 2023. Mustango: Toward controllable text-to-music generation. arXiv preprint arXiv:2311.08355 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion. arXiv preprint arXiv:2503.01183","author":"Ning Ziqian","year":"2025","unstructured":"Ziqian Ning, Huakang Chen, Yuepeng Jiang, Chunbo Hao, Guobin Ma, Shuai Wang, Jixun Yao, and Lei Xie. 2025. DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion. arXiv preprint arXiv:2503.01183 (2025)."},{"key":"e_1_3_2_1_36_1","volume-title":"Communicative agents for software development. arXiv preprint arXiv:2307.07924","author":"Qian Chen","year":"2023","unstructured":"Chen Qian and Xin Cong. 2023. Communicative agents for software development. arXiv preprint arXiv:2307.07924, Vol. 6, 3 (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890132"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34694"},{"key":"e_1_3_2_1_39_1","volume-title":"Dopamine Audiobook: A Training-free MLLM Agent for Emotional and Human-like Audiobook Generation. arXiv preprint arXiv:2504.11002","author":"Rong Yan","year":"2025","unstructured":"Yan Rong, Shan Yang, Guangzhi Lei, and Li Liu. 2025. Dopamine Audiobook: A Training-free MLLM Agent for Emotional and Human-like Audiobook Generation. arXiv preprint arXiv:2504.11002 (2025)."},{"key":"e_1_3_2_1_40_1","volume-title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations.","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_41_1","volume-title":"AudioX: Diffusion Transformer for Anything-to-Audio Generation. arXiv preprint arXiv:2503.10522","author":"Tian Zeyue","year":"2025","unstructured":"Zeyue Tian, Yizhu Jin, Zhaoyang Liu, Ruibin Yuan, Xu Tan, Qifeng Chen, Wei Xue, and Yike Guo. 2025. AudioX: Diffusion Transformer for Anything-to-Audio Generation. arXiv preprint arXiv:2503.10522 (2025)."},{"key":"e_1_3_2_1_42_1","volume-title":"Vidmuse: A simple video-to-music generation framework with long-short-term modeling. arXiv preprint arXiv:2406.04321","author":"Tian Zeyue","year":"2024","unstructured":"Zeyue Tian, Zhaoyang Liu, Ruibin Yuan, Jiahao Pan, Qifeng Liu, Xu Tan, Qifeng Chen, Wei Xue, and Yike Guo. 2024. Vidmuse: A simple video-to-music generation framework with long-short-term modeling. arXiv preprint arXiv:2406.04321 (2024)."},{"key":"e_1_3_2_1_43_1","unstructured":"Andros Tjandra Yi-Chiao Wu Baishan Guo John Hoffman Brian Ellis Apoorv Vyas Bowen Shi Sanyuan Chen Matt Le Nick Zacharov et al. 2025. Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech Music and Sound. arXiv preprint arXiv:2502.05139 (2025)."},{"key":"e_1_3_2_1_44_1","volume-title":"SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing. arXiv preprint arXiv:2411.18983","author":"Tu Rong-Cheng","year":"2024","unstructured":"Rong-Cheng Tu, Wenhao Sun, Zhao Jin, Jingyi Liao, Jiaxing Huang, and Dacheng Tao. 2024. SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing. arXiv preprint arXiv:2411.18983 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"e_1_3_2_1_46_1","volume-title":"MotionComposer: Enhancing Rhythmic Music Generation with Adaptive Retrieval Reference. In IEEE International Conference on Acoustics, Speech and Signal Processing. 1-5.","author":"Wang Jinting","year":"2025","unstructured":"Jinting Wang, Li Liu, and Jun Wang. 2025. MotionComposer: Enhancing Rhythmic Music Generation with Adaptive Retrieval Reference. In IEEE International Conference on Acoustics, Speech and Signal Processing. 1-5."},{"key":"e_1_3_2_1_47_1","first-page":"128374","article-title":"Genartist: Multimodal llm as an agent for unified image generation and editing","volume":"37","author":"Wang Zhenyu","year":"2024","unstructured":"Zhenyu Wang, Aoxue Li, Zhenguo Li, and Xihui Liu. 2024a. Genartist: Multimodal llm as an agent for unified image generation and editing. Advances in Neural Information Processing Systems, Vol. 37 (2024), 128374-128395.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_48_1","volume-title":"Towards Controllable Speech Synthesis in the Era of Large Language Models: A Survey. arXiv preprint arXiv:2412.06602","author":"Xie Tianxin","year":"2024","unstructured":"Tianxin Xie, Yan Rong, Pengfei Zhang, and Li Liu. 2024. Towards Controllable Speech Synthesis in the Era of Large Language Models: A Survey. arXiv preprint arXiv:2412.06602 (2024)."},{"key":"e_1_3_2_1_49_1","volume-title":"FilmComposer: LLM-Driven Music Production for Silent Film Clips. arXiv preprint arXiv:2503.08147","author":"Xie Zhifeng","year":"2025","unstructured":"Zhifeng Xie, Qile He, Youjia Zhu, Qiwei He, and Mengtian Li. 2025a. FilmComposer: LLM-Driven Music Production for Silent Film Clips. arXiv preprint arXiv:2503.08147 (2025)."},{"key":"e_1_3_2_1_50_1","volume-title":"Audio-reasoner: Improving reasoning capability in large audio language models. arXiv preprint arXiv:2503.02318","author":"Xie Zhifei","year":"2025","unstructured":"Zhifei Xie, Mingbao Lin, Zihang Liu, Pengcheng Wu, Shuicheng Yan, and Chunyan Miao. 2025b. Audio-reasoner: Improving reasoning capability in large audio language models. arXiv preprint arXiv:2503.02318 (2025)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"e_1_3_2_1_52_1","volume-title":"Auffusion: Leveraging the power of diffusion and large language models for text-to-audio generation","author":"Xue Jinlong","year":"2024","unstructured":"Jinlong Xue, Yayue Deng, Yingming Gao, and Ya Li. 2024. Auffusion: Leveraging the power of diffusion and large language models for text-to-audio generation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Audio augmented reality: A systematic review of technologies, applications, and future research directions. journal of the audio engineering society","author":"Yang Jing","year":"2022","unstructured":"Jing Yang, Amit Barde, and Mark Billinghurst. 2022. Audio augmented reality: A systematic review of technologies, applications, and future research directions. journal of the audio engineering society, Vol. 70, 10 (2022), 788-809."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447898"},{"key":"e_1_3_2_1_55_1","volume-title":"Kun Zhou, et al.","author":"Zhang Chong","year":"2025","unstructured":"Chong Zhang, Yukun Ma, Qian Chen, Wen Wang, Shengkui Zhao, Zexu Pan, Hao Wang, Chongjia Ni, Trung Hieu Nguyen, Kun Zhou, et al., 2025a. InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation. arXiv preprint arXiv:2503.00084 (2025)."},{"key":"e_1_3_2_1_56_1","volume-title":"Foleycrafter: Bring silent videos to life with lifelike and synchronized sounds. arXiv preprint arXiv:2407.01494","author":"Zhang Yiming","year":"2024","unstructured":"Yiming Zhang, Yicheng Gu, Yanhong Zeng, Zhening Xing, Yuancheng Wang, Zhizheng Wu, and Kai Chen. 2024. Foleycrafter: Bring silent videos to life with lifelike and synchronized sounds. arXiv preprint arXiv:2407.01494 (2024)."},{"key":"e_1_3_2_1_57_1","volume-title":"Long-Video Audio Synthesis with Multi-Agent Collaboration. arXiv preprint arXiv:2503.10719","author":"Zhang Yehang","year":"2025","unstructured":"Yehang Zhang, Xinli Xu, Xiaojie Xu, Li Liu, and Yingcong Chen. 2025b. Long-Video Audio Synthesis with Multi-Agent Collaboration. arXiv preprint arXiv:2503.10719 (2025)."},{"key":"e_1_3_2_1_58_1","volume-title":"Automatic Chain of Thought Prompting in Large Language Models. In The Eleventh International Conference on Learning Representations.","author":"Zhang Zhuosheng","year":"2023","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2023. Automatic Chain of Thought Prompting in Large Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681680"},{"key":"e_1_3_2_1_60_1","volume-title":"GVMGen: A General Video-to-Music Generation Model with Hierarchical Attentions. arXiv preprint arXiv:2501.09972","author":"Zuo Heda","year":"2025","unstructured":"Heda Zuo, Weitao You, Junxian Wu, Shihong Ren, Pei Chen, Mingxu Zhou, Yujia Lu, and Lingyun Sun. 2025. GVMGen: A General Video-to-Music Generation Model with Hierarchical Attentions. arXiv preprint arXiv:2501.09972 (2025)."}],"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\/3746027.3755758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:58:56Z","timestamp":1765339136000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755758"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":60,"alternative-id":["10.1145\/3746027.3755758","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755758","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"}}]}}