author={Guojian Li and Chengyou Wang and Hongfei Xue and Shuiyuan Wang and Dehui Gao and Zihan Zhang and Yuke Lin and Wenjie Li and Longshuai Xiao and Zhonghua Fu and Lei Xie},
title={{Easy Turn}: Integrating Acoustic and Linguistic Modalities for Robust Turn-Taking in Full-Duplex Spoken Dialogue Systems},
booktitle={Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
year={2026},
url={https://arxiv.org/abs/2509.23938}
}
@article{wang2026fastturn,
author={Chengyou Wang and Hongfei Xue and Mingchen Shao and Chunjiang He and Jingbin Hu and Shuiyuan Wang and Bo Wu and Yuyu Ji and Jimeng Zheng and Ruofei Chen and Zhou Zhu and Lei Xie},
title={{FastTurn}: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection},
journal={arXiv preprint arXiv:2604.01897},
year={2026}
}
@inproceedings{wagner2024ddsd,
author={Dominik Wagner and Alexander Churchill and Siddharth Sigtia and Panayiotis Georgiou and Matt Mirsamadi and Aarshee Mishra and Erik Marchi},
title={A Multimodal Approach to Device-Directed Speech Detection with Large Language Models},
booktitle={Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
author={Junhyeok Kim and Min Soo Kim and Jiwan Chung and Jungbin Cho and Jisoo Kim and Sungwoong Kim and Gyeongbo Sim and Youngjae Yu},
title={{EgoSpeak}: Learning When to Speak for Egocentric Conversational Agents in the Wild},
booktitle={Findings of the Association for Computational Linguistics: NAACL},
pages={2990--3005},
year={2025},
doi={10.18653/v1/2025.findings-naacl.163}
}
@article{donley2021easycom,
author={Jacob Donley and Vladimir Tourbabin and Jung-Suk Lee and Mark Broyles and Hao Jiang and Jie Shen and Maja Pantic and Vamsi Krishna Ithapu and Ravish Mehra},
title={{EasyCom}: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments},
journal={arXiv preprint arXiv:2107.04174},
year={2021}
}
@article{xu2025qwenomni,
author={Jin Xu and Zhifang Guo and Jinzheng He and Hangrui Hu and Ting He and Shuai Bai and Keqin Chen and Jialin Wang and Yang Fan and Kai Dang and Bin Zhang and Xiong Wang and Yunfei Chu and Junyang Lin},
title={{Qwen2.5-Omni Technical Report}},
journal={arXiv preprint arXiv:2503.20215},
year={2025}
}
@inproceedings{serj2024threem,
author={Mehdi Fatan Serj and Emanuele Mincato and Dimitra Pintzou and Mariella Dimiccoli},
title={{3M-Transformer}: A Multi-Stage Multi-Stream Multimodal Transformer for Embodied Turn-Taking Prediction},
booktitle={Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages={8050--8054},
year={2024},
doi={10.1109/ICASSP48485.2024.10448136}
}
@inproceedings{jia2024avconv,
author={Wenqi Jia and Miao Liu and Hao Jiang and Ishwarya Ananthabhotla and James M. Rehg and Vamsi Krishna Ithapu and Ruohan Gao},
title={The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={26396--26405},
year={2024}
}
@article{qi2026muvap,
author={Haotian Qi and Gabriel Skantze},
title={{MuVAP}: Multimodal Multiparty Voice Activity Projection for Turn-Taking Prediction in the Wild},
journal={arXiv preprint arXiv:2606.16731},
year={2026}
}
@inproceedings{huh2025egoasd,
author={Jaesung Huh and Juan Azcarreta Ortiz and Anurag Kumar and Ashutosh Pandey and Ali Aroudi and Daniel D. E. Wong and Francesco Nesta and Buye Xu and Jacob Donley},
title={Advancing Active Speaker Detection for Egocentric Videos},
booktitle={Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
