{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:57:13Z","timestamp":1782316633489,"version":"3.54.5"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032297549","type":"print"},{"value":"9783032297556","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-29755-6_25","type":"book-chapter","created":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:43:13Z","timestamp":1782315793000},"page":"369-383","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MusicTutor: Facilitating Goal-Oriented Singing Practice via\u00a0Multi-agent Tutoring Framework"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6891-0156","authenticated-orcid":false,"given":"Tengteng","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4667-6614","authenticated-orcid":false,"given":"Xueyi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6604-475X","authenticated-orcid":false,"given":"Teng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5225-2195","authenticated-orcid":false,"given":"Mingliang","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0491-307X","authenticated-orcid":false,"given":"Zitao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5605-7397","authenticated-orcid":false,"given":"Weiqi","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"25_CR1","unstructured":"Chen, Z., et al.: Advancing mathematical reasoning in language models: the impact of problem-solving data, data synthesis methods, and training stages. In: Proceedings of the Thirteenth International Conference on Learning Representations. Singapore (2025)"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Dai, S., Liu, M.Y., Valle, R., Gururani, S.: Expressivesinger: multilingual and multi-style score-based singing voice synthesis with expressive performance control. In: Proceedings of the 32nd ACM International Conference on Multimedia. Melbourne VIC, Australia (2024)","DOI":"10.1145\/3664647.3681642"},{"key":"25_CR3","unstructured":"Ding, D., et\u00a0al.: Kimi-audio technical report (2025). arXiv preprint arXiv:2504.18425"},{"key":"25_CR4","unstructured":"Du, Y., Li, S., Torralba, A., Tenenbaum, J.B., Mordatch, I.: Improving factuality and reasoning in language models through multiagent debate. In: Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria (2024)"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Fang, C.M., Huang, L., Kuang, Q., Lieberman, Z., Maes, P., Ishii, H.: An accessible, three-axis plotter for enhancing calligraphy learning through generated motion. In: Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, Honolulu, HI, USA (2024)","DOI":"10.1145\/3613904.3642792"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Gemicioglu, T., et al.: Passive haptic rehearsal for augmented piano learning in the wild. Proc. ACM Interact. Mobile Wearable Ubiquit. Technol. 8, 187:1\u2013187:26 (2024)","DOI":"10.1145\/3699748"},{"key":"25_CR7","doi-asserted-by":"publisher","first-page":"2422","DOI":"10.1109\/TASLP.2022.3190732","volume":"30","author":"C Gupta","year":"2022","unstructured":"Gupta, C., Li, H., Goto, M.: Deep learning approaches in topics of singing information processing. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 2422\u20132451 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Hsieh, P.C., Shen, Y.L., Tran, N.S., Chi, T.S.: Tonality-based accompaniment-guided automatic singing evaluation. In: Proceedings of the 26th Annual Conference of the International Speech Communication Association, Rotterdam, The Netherlands (2025)","DOI":"10.21437\/Interspeech.2025-1015"},{"key":"25_CR9","doi-asserted-by":"publisher","first-page":"2751","DOI":"10.1109\/TASLP.2023.3294712","volume":"31","author":"S Kim","year":"2023","unstructured":"Kim, S., Kim, Y., Jun, J., Kim, I.: Muse-SVS: multi-singer emotional singing voice synthesizer that controls emotional intensity. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 2751\u20132764 (2023)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"25_CR10","unstructured":"Kong, M., Wang, Z., Shu, Y., Dai, Z.: Meta-prompt optimization for LLM-based sequential decision making (2025). arXiv preprint arXiv:2502.00728"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Li, G., Hammoud, H.A.A.K., Itani, H., Khizbullin, D., Ghanem, B.: Camel: communicative agents for mind exploration of large language model society. In: Proceedings of the 37th Conference on Neural Information Processing Systems, New Orleans, LA, USA (2023)","DOI":"10.52202\/075280-2264"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: CTAL: pre-training cross-modal transformer for audio-and-language representations. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Online and Punta Cana, Dominican Republic (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.323"},{"key":"25_CR13","first-page":"1","volume":"16","author":"W Li","year":"2025","unstructured":"Li, W., et al.: AI-assisted feedback and reflection in vocal music training: effects on metacognition and singing performance. Front. Psychol. 16, 1\u201316 (2025)","journal-title":"Front. Psychol."},{"key":"25_CR14","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1109\/TASLPRO.2025.3642728","volume":"34","author":"X Li","year":"2025","unstructured":"Li, X., Zhou, Z., Liu, Z., Wu, Y., Luo, W.: A synergistic multi-agent framework for camouflage attack on large language models. IEEE Trans. Audio Speech Lang. Process. 34, 299\u2013310 (2025)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"25_CR15","unstructured":"Li, Y., et\u00a0al.: MERT: acoustic music understanding model with large-scale self-supervised training. In: Proceedings of the 12th International Conference on Learning Representations. Vienna, Austria (2024)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: EYESEE: enhancing art appreciation through anthropomorphic interpretations from multiple perspectives. In: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, Yokohama, Japan (2025)","DOI":"10.1145\/3706598.3714042"},{"key":"25_CR17","unstructured":"Liu, T., et al.: From text to talk: audio-language model needs non-autoregressive joint training. In: Proceedings of the 14th International Conference on Learning Representations. Rio de Janeiro, Brazil (2026)"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Dolphin: a spoken language proficiency assessment system for elementary education. In: Proceedings of The Web Conference 2020. Taipei, Taiwan (2020)","DOI":"10.1145\/3366423.3380018"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: What are step-level reward models rewarding? Counterintuitive findings from MCTS-boosted mathematical reasoning. In: Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence. Philadelphia, PA, USA (2025)","DOI":"10.1609\/aaai.v39i23.34663"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Park, J.S., O\u2019Brien, J.C., Cai, C.J., Morris, M.R., Liang, P., Bernstein, M.S.: Generative agents: interactive simulacra of human behavior. In: Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. San Francisco, CA, USA (2023)","DOI":"10.1145\/3586183.3606763"},{"key":"25_CR21","unstructured":"Piao, Z., Xia, G.: Sensing the breath: a multimodal singing tutoring interface with breath guidance. In: Proceedings of the International Conference on New Interfaces for Musical Expression (2022)"},{"key":"25_CR22","unstructured":"Santos, A.N.d., Masiero, B.S.: A survey on 30+ years of automatic singing assessment and singing information processing (2026). arXiv preprint arXiv:2601.12153"},{"key":"25_CR23","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1109\/TAFFC.2024.3507192","volume":"16","author":"A Sayal","year":"2024","unstructured":"Sayal, A., et al.: Decoding musical valence and arousal: exploring the neural correlates of music-evoked emotions and the role of expressivity features. IEEE Trans. Affect. Comput. 16, 1247\u20131259 (2024)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Tao, W., et al.: MAGIS: LLM-based multi-agent framework for GitHub issue resolution. In: Proceedings of the 38th Conference on Neural Information Processing Systems. Vancouver, BC, Canada (2024)","DOI":"10.52202\/079017-1647"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wang, Z., Su, Y., Tong, H., Song, Y.: Rethinking the bounds of LLM reasoning: are multi-agent discussions the key? In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok, Thailand (2024)","DOI":"10.18653\/v1\/2024.acl-long.331"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Singing timbre popularity assessment based on multimodal large foundation model. In: Proceedings of the 33rd ACM International Conference on Multimedia. Dublin, Ireland (2025)","DOI":"10.1145\/3746027.3758148"},{"key":"25_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.learninstruc.2025.102278","volume":"102","author":"D Wu","year":"2026","unstructured":"Wu, D.: Utilizing ai and machine learning in vocal training programs: a contemporary approach. Learn. Instr. 102, 1\u20139 (2026)","journal-title":"Learn. Instr."},{"key":"25_CR28","unstructured":"Xu, H., Chen, S., Zhang, Y.: Magical brush: a symbol-based modern Chinese painting system for novices. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, Hamburg, Germany (2023)"},{"key":"25_CR29","unstructured":"Xu, J., Guo, Z., Hu, H., Chu, Y., Wang, X.: Qwen3-omni technical report (2025). arXiv preprint arXiv:2509.17765"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Xu, W., et al.: Singmaster: a sight-singing evaluation system of shoot and sing based on smartphone. In: Proceedings of the 30th ACM International Conference on Multimedia, Lisboa, Portugal (2022)","DOI":"10.1145\/3503161.3547727"},{"key":"25_CR31","doi-asserted-by":"publisher","first-page":"3881","DOI":"10.1109\/TMM.2022.3168132","volume":"25","author":"W Yang","year":"2023","unstructured":"Yang, W., Wang, X., Tian, B., Xu, W., Cheng, W.: A multi-stage automatic evaluation system for sight-singing. IEEE Trans. Multimedia 25, 3881\u20133893 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Yue, Y., et al.: Masrouter: Learning to route LLMS for multi-agent systems. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics. Vienna, Austria (2025)","DOI":"10.18653\/v1\/2025.acl-long.757"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Chain of agents: large language models collaborating on long-context tasks. In: Proceedings of the 38th Conference on Neural Information Processing Systems. Vancouver, BC, Canada (2024)","DOI":"10.52202\/079017-4202"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-29755-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:44:00Z","timestamp":1782315840000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29755-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"ISBN":["9783032297549","9783032297556"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29755-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"25 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIED","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence in Education","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seoul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.aied-conference.org\/2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}