Conference

Band-Split Self-supervised Mamba for Infant-centered Audio Analysis

[PDF]

Xulin Fan, Jialu Li, Mark Hasegawa-Johnson, and Nancy L. McElwain

Published in the Proceedings of Interspeech, Rotterdam, Netherlands, August 2025


Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis

[PDF] [Model Weights (Hugging Face)][Code]

Jialu Li, Mark Hasegawa-Johnson, and Karrie Karahalios

Published in the Proceedings of Interspeech, Kos Island, Greece, September 2024


Sound Tagging in Infant-centric Home Soundscapes

[PDF]

Mohammad Nur Hossain Khan, Jialu Li, Nancy L. McElwain, Mark Hasegawa-Johnson, and Bashima Islam

Published in IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE 2024), February 2024


Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio 

[PDF] [Model Weights (Hugging Face)] [Code]

Jialu Li, Mark Hasegawa-Johnson, and Nancy L. McElwain

Published in the Proceedings of Interspeech, Dublin, Ireland, August 2023


Listen, Decipher and Sign: Toward Unsupervised Speech-to-Sign Language Recognition 

[PDF]

Liming Wang, Junrui Ni, Heting Gao, Jialu Li, Kai Chieh Chang, Xulin Fan, Junkai Wu, Mark Hasegawa-Johnson, and Chang D. Yoo

Published in the Findings of Association for Computational Linguistics (Findings of ACL’23), July 2023


Autosegmental Neural Nets: Should Phones and Tones be Synchronous or Asynchronous? 

[PDF] [Highlight Video] [Video] [Code]

Jialu Li and Mark Hasegawa-Johnson

Published in the Proceedings of Interspeech, Shanghai, China, October 2020