Tiantian Feng

SAIL Lab, University of Southern California. tiantiaf@usc.edu


This amazing picture was taken by my wife at Skyline Trail, Mount Rainier, 2023.

PS: Prepare enough water for this trail but make sure you are not the one carrying it.

My name is Tiantian Feng, and I grew up in Leshan, China, which is famously for Leshan Giant Buddha. I studied both in Chengdu (both middle school and high school at Chengdu Foreign Language School) and Nanjing (Nanjing University of Posts and Telecommunications, undergraduate). I obtained my master degree at the University of Southern California afterwards. I recently completed my Ph.D. in the Thomas Lord Department of Computer Science at University of Southern California in 2023. I am fortunate to be advised by Professor Shrikanth Narayanan, a globally recognized scientist in speech modeling, linguistics, affective computing, and human understanding.

My research focuses on leveraging sensors and computational methods for understanding natural human behaviors, also with a particular emphasis on inclusiveness and privacy. My research invovles applications such as speech understanding, multimodal understanding, and bio-signal processing, etc. Additionally, I have hands-on experience in industrial sensor design and deploying sensors in research studies. I have interned at both Meta and Amazon as the research scientist.

I am currently a postdoc researcher in SAIL lab at USC, and I am actively looking for tenure-track or similar positions in academia. Don’t hesitate to contact me if you would like to collaborate.


Apr 22, 2024 Receive IEEE EMBC NextGen Scholar Award!
Apr 15, 2024 1 conference paper got accepted to 2024 EMBC! Congrats to all co-authors!
Apr 12, 2024 Give 2 oral and 1 poster presentation at 2024 ICASSP for 2 conference papers and 1 workshop paper (all first author)! My colleagues presented 2 conference papers that I collabrated with!
Apr 05, 2024 I will be hosting Trustworthy Speech Processing Satellite Workshop at ICASSP 2024, April 15th, 2024 from 2:00 PM to 5:30 PM KST (Room AB203)! Please join us if you are interested in making speech processing safer, more private, and more inclusive!
Jan 29, 2024 Received 2024 ICASSP travel grant!
Dec 15, 2023 4 conference papers and 1 workshop paper got accepted to 2024 ICASSP! Congrats to all co-authors!
Dec 11, 2023 Successfully defended my Ph.D. thesis: Generative Foundation Model Assisted Privacy-Enhancing Computing in Human-Centered Machine Intelligence!
Oct 27, 2023 Received Outstanding Poster Presentation - 2023 Electrical Engineering Research Festival - Ming Hsieh Department of Electrical and Computer Engineering.
Sep 11, 2023 Oral presentation of my work funded by Amazon research at ACII 2023 in MIT Media Lab, Boston - PEFT-SER: On the use of parameter efficient transfer learning approaches for speech emotion recognition using pre-trained speech models!
Aug 08, 2023 Oral presentation of my work collabrated with Amazon Alexa and OSU at SIGKDD 2023 - FedMultimodal: A Benchmark for Multimodal Federated Learning!

Selected Publications

  1. Scientific Data Dataset
    TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers
    Karel Mundnich , Brandon M Booth , Michelle l’Hommedieu , Tiantian Feng , Benjamin Girault , Justin L’hommedieu , Mackenzie Wildman , Sophia Skaaden , Amrutha Nadarajan , Jennifer L Villatte , and 1 more author
    Scientific Data, 2020
  2. Scientific Data Dataset
    TILES-2019: A longitudinal physiologic and behavioral data set of medical residents in an intensive care unit
    Joanna C Yau , Benjamin Girault , Tiantian Feng , Karel Mundnich , Amrutha Nadarajan , Brandon M Booth , Emilio Ferrara , Kristina Lerman , Eric Hsieh , and Shrikanth Narayanan
    Scientific Data, 2022
  3. ACM Multimedia Dataset
    MM-AU: Towards Multimodal Understanding of Advertisement Videos
    Digbalay Bose , Rajat Hebbar , Tiantian Feng , Krishna Somandepalli , Anfeng Xu , and Shrikanth Narayanan
    In Proceedings of the 31st ACM International Conference on Multimedia , 2023
  4. Preprint Generative AI
    Can Text-to-image Model Assist Multi-modal Learning for Visual Recognition with Visual Modality Missing?
    Tiantian Feng , Daniel Yang , Digbalay Bose , and Shrikanth Narayanan
    arXiv preprint arXiv:2402.09036, 2024
  5. Voice Privacy Generative AI
    Unlocking Foundation Models for Privacy-Enhancing Speech Understanding: An Early Study on Low Resource Speech Training Leveraging Label-guided Synthetic Speech Content
    Tiantian Feng , Digbalay Bose , Xuan Shi , and Shrikanth Narayanan
    arXiv preprint arXiv:2306.07791, 2023
  6. Preprint Generative AI
    GPT-FL: Generative pre-trained model-assisted federated learning
    Tuo Zhang* , Tiantian Feng* , Samiul Alam , Mi Zhang , Shrikanth S Narayanan , and Salman Avestimehr
    arXiv preprint arXiv:2306.02210, 2023
  7. Journal Trustworthiness
    A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness
    Tiantian Feng , Rajat Hebbar , Nicholas Mehlman , Xuan Shi , Aditya Kommineni , and Shrikanth Narayanan
    APSIPA Transactions on Signal and Information Processing, 2023
  8. ICASSP 2022 Trustworthiness
    Enhancing privacy through domain adaptive noise injection for speech emotion recognition
    Tiantian Feng , Hanieh Hashemi , Murali Annavaram , and Shrikanth S Narayanan
    In ICASSP 2022-2022 IEEE international conference on acoustics, speech and signal processing (ICASSP) , 2022
  9. ICASSP 2024 Trustworthiness
    TRUST-SER: On The Trustworthiness Of Fine-Tuning Pre-Trained Speech Embeddings For Speech Emotion Recognition
    Tiantian Feng , Rajat Hebbar , and Shrikanth Narayanan
    In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2024
  10. SIGKDD 2023 Federated Learning
    FedMultimodal: A Benchmark for Multimodal Federated Learning
    Tiantian Feng , Digbalay Bose , Tuo Zhang , Rajat Hebbar , Anil Ramakrishna , Rahul Gupta , Mi Zhang , Salman Avestimehr , and Shrikanth Narayanan
    In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , 2023
  11. ICASSP 2023 Federated Learning
    FedAudio: A federated learning benchmark for audio tasks
    Tuo Zhang , Tiantian Feng , Samiul Alam , Sunwoo Lee , Mi Zhang , Shrikanth S Narayanan , and Salman Avestimehr
    In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2023
  12. ICASSP TSP 2024 Federated Learning
    Partial federated learning: Unlocking non-biometric text information sharing for federated learning
    Tiantian Feng , Anil Ramakrishna , Jimit Majmudar , Charith Peris , Jixuan Wang , Clement Chung , Richard Zemel , Morteza Ziyadi , and Rahul Gupta
  13. INTERSPEECH 2022 Federated Learning
    User-Level Differential Privacy against Attribute Inference Attack of Speech Emotion Recognition on Federated Learning
    Tiantian Feng , Raghuveer Peri , and Shrikanth Narayanan
    In Proc. Interspeech 2022 , 2022
  14. ICASSP 2024 Foundation Model
    Foundation Model Assisted Automatic Speech Emotion Recognition: Transcribing, Annotating, and Augmenting
    Tiantian Feng , and Shrikanth Narayanan
    In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2024
  15. ACII 2023 Foundation Model
    PEFT-SER: On the use of parameter efficient transfer learning approaches for speech emotion recognition using pre-trained speech models
    Tiantian Feng , and Shrikanth Narayanan
    In 2023 11th International Conference on Affective Computing and Intelligent Interaction (ACII) , 2023
  16. Preprint Wearables
    Understanding Stress, Burnout, and Behavioral Patterns in Medical Residents Using Large-scale Longitudinal Wearable Recordings
    Tiantian Feng , and Shrikanth Narayanan
    arXiv preprint arXiv:2402.09028, 2024
  17. Scientific Reports Wearables
    A multimodal analysis of physical activity, sleep, and work shift in nurses with wearable sensor data
    Tiantian Feng , Brandon M Booth , Brooke Baldwin-Rodrı́guez , Felipe Osorno , and Shrikanth Narayanan
    Scientific reports, 2021
  18. ACM Transactions Wearables
    Temporal dynamics of workplace acoustic scenes: Egocentric analysis and prediction
    Arindam Jati , Amrutha Nadarajan , Raghuveer Peri , Karel Mundnich , Tiantian Feng , Benjamin Girault , and Shrikanth Narayanan
    IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
  19. Mobisys Workshop Wearables
    Tiles Audio Recorder: An Unobtrusive Wearable Solution to Track Audio Activity
    Tiantian Feng , Amrutha Nadarajan , Colin Vaz , Brandon Booth , and Shrikanth Narayanan
    In Proceedings of the 4th ACM Workshop on Wearable Systems and Applications , 2018
  20. ICASSP 2019 Wearables
    Discovering optimal variable-length time series motifs in large-scale wearable recordings of human bio-behavioral signals
    Tiantian Feng , and Shrikanth S Narayanan
    In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2019