Publications

@inproceedings{ahmed_asar_2023,

title = {ASAR Dataset and Computational Model for Affective State Recognition During ARAT Assessment for Upper Extremity Stroke Survivors},

author = {Tamim Ahmed and Thanassis Rikakis and Aisling Kelliher and Mohammad Soleymani},

url = {https://dl.acm.org/doi/10.1145/3610661.3617154},

doi = {10.1145/3610661.3617154},

isbn = {979-8-4007-0321-8},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

booktitle = {International Cconference on Multimodal Interaction},

pages = {11–15},

publisher = {ACM},

address = {Paris France},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{andrist_platform_2023,

title = {Platform for Situated Intelligence and OpenSense: A Tutorial on Building Multimodal Interactive Applications for Research},

author = {Sean Andrist and Dan Bohus and Zongjian Li and Mohammad Soleymani},

url = {https://dl.acm.org/doi/10.1145/3610661.3617603},

doi = {10.1145/3610661.3617603},

isbn = {979-8-4007-0321-8},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

booktitle = {International Cconference on Multimodal Interaction},

pages = {105–106},

publisher = {ACM},

address = {Paris France},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tran_multimodal_2023,

title = {Multimodal Analysis and Assessment of Therapist Empathy in Motivational Interviews},

author = {Trang Tran and Yufeng Yin and Leili Tavabi and Joannalyn Delacruz and Brian Borsari and Joshua D Woolley and Stefan Scherer and Mohammad Soleymani},

url = {https://dl.acm.org/doi/10.1145/3577190.3614105},

doi = {10.1145/3577190.3614105},

isbn = {979-8-4007-0055-2},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

booktitle = {INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION},

pages = {406–415},

publisher = {ACM},

address = {Paris France},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gainer_divis_2023,

title = {DIVIS: Digital Interactive Victim Intake Simulator},

author = {Alesia Gainer and Allison Aptaker and Ron Artstein and David Cobbins and Mark Core and Carla Gordon and Anton Leuski and Zongjian Li and Chirag Merchant and David Nelson and Mohammad Soleymani and David Traum},

url = {https://dl.acm.org/doi/10.1145/3570945.3607328},

doi = {10.1145/3570945.3607328},

isbn = {978-1-4503-9994-4},

year  = {2023},

date = {2023-09-01},

urldate = {2024-02-20},

booktitle = {Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents},

pages = {1–2},

publisher = {ACM},

address = {Würzburg Germany},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tran_personalized_2023,

title = {Personalized Adaptation with Pre-trained Speech Encoders for Continuous Emotion Recognition},

author = {Minh Tran and Yufeng Yin and Mohammad Soleymani},

url = {https://www.isca-speech.org/archive/interspeech_2023/tran23c_interspeech.html},

doi = {10.21437/Interspeech.2023-2170},

year  = {2023},

date = {2023-08-01},

urldate = {2023-08-23},

booktitle = {INTERSPEECH 2023},

pages = {636–640},

publisher = {ISCA},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tran_speech_2023,

title = {A Speech Representation Anonymization Framework via Selective Noise Perturbation},

author = {Minh Tran and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/document/10095173/},

doi = {10.1109/ICASSP49357.2023.10095173},

isbn = {978-1-7281-6327-7},

year  = {2023},

date = {2023-06-01},

urldate = {2023-08-23},

booktitle = {ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {1–5},

publisher = {IEEE},

address = {Rhodes Island, Greece},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{yin_x-norm_2022,

title = {X-Norm: Exchanging Normalization Parameters for Bimodal Fusion},

author = {Yufeng Yin and Jiashu Xu and Tianxin Zu and Mohammad Soleymani},

url = {https://dl.acm.org/doi/10.1145/3536221.3556581},

doi = {10.1145/3536221.3556581},

isbn = {978-1-4503-9390-4},

year  = {2022},

date = {2022-11-01},

urldate = {2023-08-24},

booktitle = {INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION},

pages = {605–614},

publisher = {ACM},

address = {Bengaluru India},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhang_speech_2022,

title = {Speech Behavioral Markers Align on Symptom Factors in Psychological Distress},

author = {Larry Zhang and Jacek Kolacz and Albert Rizzo and Stefan Scherer and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/abstract/document/9953849},

doi = {10.1109/ACII55700.2022.9953849},

year  = {2022},

date = {2022-10-01},

booktitle = {2022 10th International Conference on Affective Computing and Intelligent Interaction (ACII)},

pages = {1–8},

abstract = {Automatic detection of psychological disorders has gained significant attention in recent years due to the rise in their prevalence. However, the majority of studies have overlooked the complexity of disorders in favor of a “present/not present” dichotomy in representing disorders. Recent psychological research challenges favors transdiagnostic approaches, moving beyond general disorder classifications to symptom level analysis, as symptoms are often not exclusive to individual disorder classes. In our study, we investigated the link between speech signals and psychological distress symptoms in a corpus of 333 screening interviews from the Distress Analysis Interview Corpus (DAIC). Given the semi-structured organization of interviews, we aggregated speech utterances from responses to shared questions across interviews. We employed deterministic sample selection in classification to rank salient questions for eliciting symptom-specific behaviors in order to predict symptom presence. Some questions include “Do you find therapy helpful?” and “When was the last time you felt happy?”. The prediction results align closely to the factor structure of psychological distress symptoms, linking speech behaviors primarily to somatic and affective alterations in both depression and PTSD. This lends support for the transdiagnostic validity of speech markers for detecting such symptoms. Surprisingly, we did not find a strong link between speech markers and cognitive or psychomotor alterations. This is surprising, given the complexity of motor and cognitive actions required in speech production. The results of our analysis highlight the importance of aligning affective computing research with psychological research to investigate the use of automatic behavioral sensing to assess psychiatric risk.},

note = {ISSN: 2156-8111},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tran_pre-trained_2022,

title = {A Pre-Trained Audio-Visual Transformer for Emotion Recognition},

author = {Minh Tran and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/document/9747278/},

doi = {10.1109/ICASSP43922.2022.9747278},

isbn = {978-1-6654-0540-9},

year  = {2022},

date = {2022-05-01},

urldate = {2022-09-23},

booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {4698–4702},

publisher = {IEEE},

address = {Singapore, Singapore},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhu_self-supervised_2022,

title = {Self-Supervised Learning for Sentiment Analysis via Image-Text Matching},

author = {Haidong Zhu and Zhaoheng Zheng and Mohammad Soleymani and Ram Nevatia},

url = {https://ieeexplore.ieee.org/document/9747819/},

doi = {10.1109/ICASSP43922.2022.9747819},

isbn = {978-1-6654-0540-9},

year  = {2022},

date = {2022-05-01},

urldate = {2022-09-23},

booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {1710–1714},

publisher = {IEEE},

address = {Singapore, Singapore},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tran_modeling_2021,

title = {Modeling Dynamics of Facial Behavior for Mental Health Assessment},

author = {Minh Tran and Ellen Bradley and Michelle Matvey and Joshua Woolley and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/document/9666955/},

doi = {10.1109/FG52635.2021.9666955},

isbn = {978-1-6654-3176-7},

year  = {2021},

date = {2021-12-01},

urldate = {2022-09-23},

booktitle = {2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)},

pages = {1–5},

publisher = {IEEE},

address = {Jodhpur, India},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{yin_self-supervised_2021,

title = {Self-Supervised Patch Localization for Cross-Domain Facial Action Unit Detection},

author = {Yufeng Yin and Liupei Lu and Yizhen Wu and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/document/9667048/},

doi = {10.1109/FG52635.2021.9667048},

isbn = {978-1-6654-3176-7},

year  = {2021},

date = {2021-12-01},

urldate = {2022-09-23},

booktitle = {2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)},

pages = {1–8},

publisher = {IEEE},

address = {Jodhpur, India},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kontogiorgos_systematic_2021,

title = {A Systematic Cross-Corpus Analysis of Human Reactions to Robot Conversational Failures},

author = {Dimosthenis Kontogiorgos and Minh Tran and Joakim Gustafson and Mohammad Soleymani},

url = {https://dl.acm.org/doi/10.1145/3462244.3479887},

doi = {10.1145/3462244.3479887},

isbn = {978-1-4503-8481-0},

year  = {2021},

date = {2021-10-01},

urldate = {2022-09-23},

booktitle = {Proceedings of the 2021 International Conference on Multimodal Interaction},

pages = {112–120},

publisher = {ACM},

address = {Montréal QC Canada},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{yin_contrastive_2021,

title = {Contrastive Learning for Domain Transfer in Cross-Corpus Emotion Recognition},

author = {Yufeng Yin and Liupei Lu and Yao Xiao and Zhi Xu and Kaijie Cai and Haonan Jiang and Jonathan Gratch and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/document/9597453/},

doi = {10.1109/ACII52823.2021.9597453},

isbn = {978-1-6654-0019-0},

year  = {2021},

date = {2021-09-01},

urldate = {2022-09-23},

booktitle = {2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII)},

pages = {1–8},

publisher = {IEEE},

address = {Nara, Japan},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{he_speaker_2021,

title = {Speaker Turn Modeling for Dialogue Act Classification},

author = {Zihao He and Leili Tavabi and Kristina Lerman and Mohammad Soleymani},

url = {https://aclanthology.org/2021.findings-emnlp.185},

doi = {10.18653/v1/2021.findings-emnlp.185},

year  = {2021},

date = {2021-01-01},

urldate = {2022-09-23},

booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2021},

pages = {2150–2157},

publisher = {Association for Computational Linguistics},

address = {Punta Cana, Dominican Republic},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{cheng_multimodal_2021,

title = {Multimodal Phased Transformer for Sentiment Analysis},

author = {Junyan Cheng and Iordanis Fostiropoulos and Barry Boehm and Mohammad Soleymani},

url = {https://aclanthology.org/2021.emnlp-main.189},

doi = {10.18653/v1/2021.emnlp-main.189},

year  = {2021},

date = {2021-01-01},

urldate = {2022-09-23},

booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},

pages = {2447–2458},

publisher = {Association for Computational Linguistics},

address = {Online and Punta Cana, Dominican Republic},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{rayatdoost_expression-guided_2020,

title = {Expression-Guided EEG Representation Learning for Emotion Recognition},

author = {Soheil Rayatdoost and David Rudrauf and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/document/9053004/},

doi = {10.1109/ICASSP40776.2020.9053004},

isbn = {978-1-5090-6631-5},

year  = {2020},

date = {2020-05-01},

booktitle = {Proceedings of the ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {3222–3226},

publisher = {IEEE},

address = {Barcelona, Spain},

abstract = {Learning a joint and coordinated representation between different modalities can improve multimodal emotion recognition. In this paper, we propose a deep representation learning approach for emotion recognition from electroencephalogram (EEG) signals guided by facial electromyogram (EMG) and electrooculogram (EOG) signals. We recorded EEG, EMG and EOG signals from 60 participants who watched 40 short videos and self-reported their emotions. A cross-modal encoder that jointly learns the features extracted from facial and ocular expressions and EEG responses was designed and evaluated on our recorded data and MAHOB-HCI, a publicly available database. We demonstrate that the proposed representation is able to improve emotion recognition performance. We also show that the learned representation can be transferred to a different database without EMG and EOG and achieve superior performance. Methods that fuse behavioral and neural responses can be deployed in wearable emotion recognition solutions, practical in situations in which computer vision expression recognition is not feasible.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}