Fu-An Chao

Hi! I am a research assistant at National Taiwan Normal University (NTNU), where I work under the guidance of Dr. Berlin Chen. My research interests focus on deep learning techniques for speech processing and their applications, including but not limited to Speech Enhancement (SE), Robust Automatic Speech Recognition (ASR), Computer-assisted Language Learning (CALL), and Multimodal Learning.

Previously, I worked as a research & development engineer at Research Center for Psychological and Educational Testing (RCPET) in NTNU. There, I contributed to Computer-assisted Language Learning (CALL) research, with a special focus on fine-grained Automatic Pronunciation Assessment (APA) and Mispronunciation Detection and Diagnosis (MDD).

If you have questions or would like to work together, feel free to reach out through email.

news

Jan 18, 2026	One paper has been accepted to ICASSP 2026, see you in Barcelona
Jan 22, 2025	One paper has been accepted to NAACL 2025!
Mar 13, 2024	One paper has been accepted to NAACL 2024!
Dec 28, 2023	Project release - L2 Speech Synthesizer
Dec 17, 2023	I launched my website!

selected publications

Probing the Hidden Talent of ASR Foundation Models for L2 English Oral Assessment

Fu-An Chao, Bi-Cheng Yan, and Berlin Chen

In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2026

Bib PDF

@inproceedings{chao2026probinghiddentalentasr,
  title = {Probing the Hidden Talent of ASR Foundation Models for L2 English Oral Assessment},
  author = {Chao, Fu-An and Yan, Bi-Cheng and Chen, Berlin},
  booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
  year = {2026},
}

Towards Efficient and Multifaceted Computer-assisted Pronunciation Training Leveraging Hierarchical Selective State Space Model and Decoupled Cross-entropy Loss

Fu-An Chao, and Berlin Chen

In the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025

Bib PDF Code

@inproceedings{chao2025efficientmultifacetedcomputerassistedpronunciation,
  title = {Towards Efficient and Multifaceted Computer-assisted Pronunciation Training Leveraging Hierarchical Selective State Space Model and Decoupled Cross-entropy Loss},
  author = {Chao, Fu-An and Chen, Berlin},
  booktitle = {the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)},
  year = {2025},
}

An Effective Automated Speaking Assessment Approach to Mitigating Data Scarcity and Imbalanced Distribution

Tien-Hong Lo, Fu-An Chao, Tzu-I Wu, and 2 more authors

In Findings of Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024

Bib PDF

@inproceedings{lo2024effective,
  title = {An Effective Automated Speaking Assessment Approach to Mitigating Data Scarcity and Imbalanced Distribution},
  author = {Lo, Tien-Hong and Chao, Fu-An and Wu, Tzu-I and Sung, Yao-Ting and Chen, Berlin},
  booktitle = {Findings of Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)},
  year = {2024},
  pages = {1352--1362},
  doi = {10.18653/v1/2024.findings-naacl.86},
}

A Hierarchical Context-aware Modeling Approach for Multi-aspect and Multi-granular Pronunciation Assessment

Fu-An Chao, Tien-Hong Lo, Tzu-I Wu, and 2 more authors

In the 24st Annual Conference of the International Speech Communication Association (Interspeech), 2023

Bib PDF

@inproceedings{chao23hierarchical,
  author = {Chao, Fu-An and Lo, Tien-Hong and Wu, Tzu-I and Sung, Yao-Ting and Chen, Berlin},
  title = {{A Hierarchical Context-aware Modeling Approach for Multi-aspect and Multi-granular Pronunciation Assessment}},
  booktitle = {the 24st Annual Conference of the International Speech Communication Association (Interspeech)},
  year = {2023},
  pages = {974--978},
  doi = {10.21437/Interspeech.2023-550},
}

3m: An effective multi-view, multi-granularity, and multi-aspect modeling approach to english pronunciation assessment

Fu-An Chao, Tien-Hong Lo, Tzu-I Wu, and 2 more authors

In Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2022

Bib PDF

@inproceedings{chao20223m,
  title = {3m: An effective multi-view, multi-granularity, and multi-aspect modeling approach to english pronunciation assessment},
  author = {Chao, Fu-An and Lo, Tien-Hong and Wu, Tzu-I and Sung, Yao-Ting and Chen, Berlin},
  booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)},
  organization = {IEEE},
  year = {2022},
  pages = {575--582},
  doi = {10.23919/APSIPAASC55919.2022.9979979},
}