{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:34:23Z","timestamp":1776886463742,"version":"3.51.2"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11433838","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Full-Duplex-Bench: A Benchmark to Evaluate Full-Duplex Spoken Dialogue Models on Turn-taking Capabilities"],"prefix":"10.1109","author":[{"given":"Guan-Ting","family":"Lin","sequence":"first","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}]},{"given":"Jiachen","family":"Lian","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Tingle","family":"Li","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Qirui","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Washington"}]},{"given":"Gopala","family":"Anumanchipalli","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Alexander H.","family":"Liu","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S0047404500001019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2010.10.003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1037\/h0033031"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2168748.2168749"},{"key":"ref5","volume-title":"Discourse as an interactional achievement: Some uses of \u201cuh huh\u201d and other things that come between sentences","author":"Schegloff","year":"1982"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1192"},{"key":"ref7","article-title":"Moshi: a speech-text foundation model for real-time dialogue","volume-title":"Kyutai, Tech. Rep.","author":"D\u00e9fossez","year":"2024"},{"key":"ref8","article-title":"A full-duplex speech dialogue scheme based on large language model","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Wang"},{"key":"ref9","author":"Fu","year":"2024","journal-title":"Vita: Towards open-source interactive omni multimodal llm"},{"key":"ref10","author":"Wang","year":"2024","journal-title":"Freeze-omni: A smart and low latency speech-to-speech dialogue model with frozen llm"},{"key":"ref11","author":"Chen","year":"2025","journal-title":"Minmo: A multimodal large language model for seamless voice interaction"},{"key":"ref12","author":"Ji","year":"2024","journal-title":"Wavchat: A survey of spoken dialogue models"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2771"},{"key":"ref14","article-title":"Spoken question answering and speech continuation using spectrogram-powered LLM","volume-title":"The Twelfth International Conference on Learning Representations","author":"Nachmani"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1514"},{"key":"ref16","article-title":"Align-slm: Textless spoken language models with reinforcement learning from ai feedback","author":"Lin","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-612"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448257"},{"key":"ref19","author":"Huang","year":"2024","journal-title":"Dynamic-superb phase-2: A collaboratively expanding benchmark for measuring the capabilities of spoken language models with 180 tasks"},{"key":"ref20","article-title":"Voxdialogue: Can spoken dialogue systems understand information beyond words?","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Cheng"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.52202\/079017-1813","article-title":"SD-eval: A benchmark dataset for spoken dialogue understanding beyond words","volume-title":"The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Ao"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.109"},{"key":"ref23","first-page":"6626","article-title":"Advancing large language models to capture varied speaking styles and respond properly in spoken conversations","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Lin"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446933"},{"key":"ref25","first-page":"13391","article-title":"Can LLMs understand the implication of emphasized sentences in dialogue?","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","author":"Lin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00545"},{"key":"ref27","article-title":"A full-duplex speech dialogue scheme based on large language model","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Wang"},{"key":"ref28","first-page":"11543","article-title":"Beyond the turn-based game: Enabling real-time conversations with duplex models","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Zhang"},{"key":"ref29","article-title":"Parrot: Seamless spoken dialogue interaction with double-channel large language models","author":"Wang","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-95-2725-0_21"},{"key":"ref31","author":"Yu","year":"2024","journal-title":"Salmonn-omni: A codec-free llm for full-duplex speech understanding and generation"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.709"},{"key":"ref33","author":"Mai","year":"2025","journal-title":"Real-time textless dialogue generation"},{"key":"ref34","article-title":"Amazon nova sonic: Technical report and model card","author":"Intelligence","year":"2025"},{"key":"ref35","article-title":"Talking turns: Benchmarking audio foundation models on turn-taking dynamics","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Arora"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023234"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref39","author":"Chen","year":"2024","journal-title":"Voicebench: Benchmarking llm-based voice assistants"},{"key":"ref40","article-title":"The zero resource speech benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","volume-title":"NeuRIPS Workshop on Self-Supervised Learning for Speech and Audio Processing","author":"Nguyen"},{"key":"ref41","first-page":"46","article-title":"LSDSem 2017 shared task: The story cloze test","volume-title":"Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics","author":"Mostafazadeh"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-2166(99)00109-5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adf3197"},{"key":"ref44","article-title":"Preliminary notes on a possible metric which provides for a \u2018standard maximum\u2019silence of approximately one second in conversation","author":"Jefferson","year":"1989","journal-title":"Conversation: An Interdisciplinary Approach\/Multilingual Matters"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.778018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2010.08.002"},{"key":"ref47","first-page":"15503","article-title":"Large language models know what to say but not when to speak","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","author":"Umair"},{"key":"ref48","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref50","article-title":"Fisher english training speech part 1 transcripts","author":"Cieri","year":"2004","journal-title":"Philadelphia: Linguistic Data Consortium"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11433838.pdf?arnumber=11433838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:55:18Z","timestamp":1775192118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11433838","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}