120 lines
5.4 KiB
BibTeX
120 lines
5.4 KiB
BibTeX
@inproceedings{ekstedt2022vap,
|
|
author = {Erik Ekstedt and Gabriel Skantze},
|
|
title = {{Voice Activity Projection: Self-Supervised Learning of Turn-Taking Events}},
|
|
booktitle = {Proc. Interspeech 2022},
|
|
pages = {5190--5194},
|
|
year = {2022},
|
|
doi = {10.21437/Interspeech.2022-10955}
|
|
}
|
|
|
|
@inproceedings{kim2025egospeak,
|
|
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 2025},
|
|
publisher = {Association for Computational Linguistics},
|
|
address = {Albuquerque, New Mexico},
|
|
pages = {2990--3005},
|
|
year = {2025},
|
|
doi = {10.18653/v1/2025.findings-naacl.163},
|
|
url = {https://aclanthology.org/2025.findings-naacl.163/}
|
|
}
|
|
|
|
@inproceedings{russell2025mmvap,
|
|
author = {Sam O'Connor Russell and Naomi Harte},
|
|
title = {Visual Cues Enhance Predictive Turn-Taking for Two-Party Human Interaction},
|
|
booktitle = {Findings of the Association for Computational Linguistics: ACL 2025},
|
|
publisher = {Association for Computational Linguistics},
|
|
address = {Vienna, Austria},
|
|
pages = {209--221},
|
|
year = {2025},
|
|
doi = {10.18653/v1/2025.findings-acl.12},
|
|
url = {https://aclanthology.org/2025.findings-acl.12/}
|
|
}
|
|
|
|
@misc{cano2026mmvap,
|
|
author = {Antonio Cano and Guillermo P{\'e}rez and Luis Merino and Randy Gomez},
|
|
title = {Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders},
|
|
year = {2026},
|
|
eprint = {2607.07294},
|
|
archivePrefix = {arXiv},
|
|
primaryClass = {cs.RO},
|
|
note = {Accepted at IEEE RO-MAN 2026},
|
|
url = {https://arxiv.org/abs/2607.07294}
|
|
}
|
|
|
|
@article{jiang2026turnbench,
|
|
author = {Freeman Jiang and others},
|
|
title = {{TurnBench}: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue},
|
|
journal = {arXiv preprint arXiv:2608.25218},
|
|
year = {2026}
|
|
}
|
|
|
|
@inproceedings{kong2024sicnet,
|
|
author = {Deqian Kong and Furqan Khan and Xu Zhang and Prateek Singhal and Ying Nian Wu},
|
|
title = {Long-Term Social Interaction Context: The Key to Egocentric Addressee Detection},
|
|
booktitle = {Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
|
|
year = {2024}
|
|
}
|
|
|
|
@inproceedings{qi2026muvap,
|
|
author = {Haotian Qi and Gabriel Skantze},
|
|
title = {{MuVAP}: Multimodal Multiparty Voice Activity Projection for Turn-Taking Prediction in the Wild},
|
|
booktitle = {Proc. Interspeech 2026},
|
|
year = {2026},
|
|
note = {arXiv:2606.16731},
|
|
url = {https://arxiv.org/abs/2606.16731}
|
|
}
|
|
|
|
@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}
|
|
}
|
|
|
|
@article{cui2026minicpmo45,
|
|
author = {Junbo Cui and Bokai Xu and Chongyi Wang and Tianyu Yu and Weiyue Sun and Yingjing Xu and Tianran Wang and Zhihui He and Wenshuo Ma and Tianchi Cai and others},
|
|
title = {{MiniCPM-o 4.5}: Towards Real-Time Full-Duplex Omni-Modal Interaction},
|
|
journal = {arXiv preprint arXiv:2604.27393},
|
|
year = {2026}
|
|
}
|
|
|
|
@inproceedings{lee2019settransformer,
|
|
author = {Juho Lee and Yoonho Lee and Jungtaek Kim and Adam Kosiorek and Seungjin Choi and Yee Whye Teh},
|
|
title = {Set Transformer: A Framework for Attention-Based Permutation-Invariant Neural Networks},
|
|
booktitle = {Proceedings of the 36th International Conference on Machine Learning},
|
|
pages = {3744--3753},
|
|
year = {2019}
|
|
}
|
|
|
|
@inproceedings{rouditchenko2024whisperflamingo,
|
|
author = {Andrew Rouditchenko and Yuan Gong and Samuel Thomas and Leonid Karlinsky and Hilde Kuehne and Rogerio Feris and James Glass},
|
|
title = {{Whisper-Flamingo}: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation},
|
|
booktitle = {Proc. Interspeech},
|
|
pages = {2420--2424},
|
|
year = {2024}
|
|
}
|
|
|
|
@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}
|
|
}
|
|
|
|
@inproceedings{grauman2022ego4d,
|
|
author = {Kristen Grauman and Andrew Westbury and Eugene Byrne and others},
|
|
title = {{Ego4D}: Around the World in 3,000 Hours of Egocentric Video},
|
|
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
|
|
pages = {18995--19012},
|
|
year = {2022}
|
|
}
|