{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:23:26Z","timestamp":1783103006322,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533459","type":"print"},{"value":"9789819533466","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-3346-6_5","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:50:06Z","timestamp":1763790606000},"page":"62-74","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DuplexMamba: Enhancing Real-Time Speech Conversations with\u00a0Duplex and\u00a0Streaming Capabilities"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1852-3750","authenticated-orcid":false,"given":"Xiangyu","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Conghui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiejun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muyun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"5_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"5_CR2","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: A framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, 12449\u201312460 (2020)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Chen, G., et\u00a0al.: GigaSpeech: an evolving, multi-domain ASR corpus with 10,000 hours of transcribed audio. In: Annual Conference of the International Speech Communication Association, pp. 4376\u20134380 (2021)","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"5_CR4","unstructured":"Chen, Q., et\u00a0al.: Minmo: a multimodal large language model for seamless voice interaction. arXiv preprint arXiv:2501.06282 (2025)"},{"key":"5_CR5","unstructured":"Chen, Y., Yue, X., Zhang, C., Gao, X., Tan, R.T., Li, H.: VoiceBench: benchmarking LLM-based voice assistants. arXiv preprint arXiv:2410.17196 (2024)"},{"key":"5_CR6","unstructured":"Chu, Y., et\u00a0al.: Qwen2-audio technical report. arXiv preprint arXiv:2407.10759 (2024)"},{"key":"5_CR7","unstructured":"D\u00e9fossez, A., et al.: Moshi: a speech-text foundation model for real-time dialogue. arXiv preprint arXiv:2410.00037 (2024)"},{"key":"5_CR8","unstructured":"Fang, Q., Guo, S., Zhou, Y., Ma, Z., Zhang, S., Feng, Y.: Llama-Omni: seamless speech interaction with large language models. In: Proceedings of the International Conference on Learning Representations (2025)"},{"key":"5_CR9","unstructured":"Fu, C., et\u00a0al.: Vita: towards open-source interactive omni multimodal LLM. arXiv preprint arXiv:2408.05211 (2024)"},{"key":"5_CR10","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Held, W., Zhang, Y., Shi, W., et al.: Distilling an end-to-end voice assistant without instruction training data. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, pp. 7876\u20137891 (2025)","DOI":"10.18653\/v1\/2025.acl-long.388"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Hernandez, F., Nguyen, V., Ghannay, S., Tomashenko, N., Esteve, Y.: Ted-lium 3: twice as much data and corpus repartition for experiments on speaker adaptation. In: Speech and Computer: International Conference, pp. 198\u2013208 (2018)","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Huang, R., et\u00a0al.: AudioGPT: understanding and generating speech, music, sound, and talking head. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 23802\u201323804 (2024)","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, X., Li, Y.A., Florea, A.N., Han, C., Mesgarani, N.: Speech slytherin: examining the performance and efficiency of mamba for speech separation, recognition, and synthesis. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10889391"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Ma, Z., et al.: Language model can listen while speaking. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 24831\u201324839 (2025)","DOI":"10.1609\/aaai.v39i23.34665"},{"key":"5_CR16","unstructured":"OpenAI: Introducing chatgpt (2022). https:\/\/openai.com\/blog\/chatgpt"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an ASR corpus based on public domain audio books. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5206\u20135210 (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Pratap, V., Xu, Q., Sriram, A., Synnaeve, G., Collobert, R.: MLS: a large-scale multilingual dataset for speech research. In: Proceedings of Interspeech, pp. 2757\u20132761 (2020)","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"5_CR19","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: Proceedings of the 40th International Conference on Machine Learning, pp. 28492\u201328518 (2023)"},{"key":"5_CR20","unstructured":"Rubenstein, P.K., et\u00a0al.: AudioPalm: a large language model that can speak and listen. arXiv preprint arXiv:2306.12925 (2023)"},{"key":"5_CR21","unstructured":"Tang, C., et al.: Salmonn: towards generic hearing abilities for large language models. In: International Conference on Learning Representations (2024)"},{"key":"5_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Veluri, B., Peloquin, B., Yu, B., Gong, H., Gollakota, S.: Beyond turn-based interfaces: synchronous LLMs as full-duplex dialogue agents. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 21390\u201321402 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.1192"},{"key":"5_CR24","unstructured":"Wang, X., et al.: Freeze-omni: A smart and low latency speech-to-speech dialogue model with frozen LLM. In: Proceedings of International Conference on Machine Learning (2025)"},{"key":"5_CR25","unstructured":"Xie, Z., Wu, C.: Mini-omni: language models can hear, talk while thinking in streaming. arXiv preprint arXiv:2408.16725 (2024)"},{"key":"5_CR26","unstructured":"Xie, Z., Wu, C.: Mini-omni2: towards open-source GPT-4o with vision, speech and duplex capabilities. arXiv preprint arXiv:2410.11190 (2024)"},{"key":"5_CR27","unstructured":"Yao, Y., et\u00a0al.: MiniCPM-V: a GPT-4v level MLLM on your phone. arXiv preprint arXiv:2408.01800 (2024)"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, D., et al.: SpeechGPT: empowering large language models with intrinsic cross-modal conversational abilities. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 15757\u201315773 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Beyond the turn-based game: enabling real-time conversations with duplex models. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 11543\u201311557 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.644"},{"key":"5_CR30","unstructured":"Zhou, J., et al.: Instruction-following evaluation for large language models. arXiv preprint arXiv:2311.07911 (2023)"},{"key":"5_CR31","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. In: International Conference on Machine Learning (2024)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3346-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:11:06Z","timestamp":1783102266000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3346-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533459","9789819533466"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3346-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}