Journals

  1. Haolin Chen and Philip N. Garner. “Bayesian parameter-efficient fine-tuning for overcoming catastrophic forgetting” IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2024. [arXiv] [IEEE] (Idiap Paper Award 2024)

Conferences

  1. Haolin Chen and Philip N. Garner. “A Bayesian interpretation of adaptive low-rank adaptation” To appear, IEEE International Conference on Acoustics, Speech and Signal Processing 2025 (ICASSP 2025). [Link]
  2. Pavel Korshunov, Haolin Chen, Philip N. Garner, and Sébastien Marcel. “Vulnerability of automatic identity recognition to audio-visual deepfakes” In Proc. IEEE International Joint Conference on Biometrics 2023 (IJCB 2023). [arXiv] [IEEE]
  3. Haolin Chen, Mutian He, Louise Coppieters de Gibson, and Philip N. Garner. “The Idiap speech synthesis system for the Blizzard Challenge 2023” In Proc. 18th Blizzard Challenge Workshop (Blizzard 2023). [Link]
  4. Haolin Chen and Philip N. Garner. “Diffusion transformer for adaptive text-to-speech” In Proc. 12th ISCA Speech Synthesis Workshop (SSW 2023). [Link]
  5. Florian Mai, Arnaud Pannatier, Fabio Fehr, Haolin Chen, François Marelli, Francois Fleuret, and James Henderson. “HyperMixer: An MLP-based low cost alternative to transformers” In Proc. 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023). [Link]
  6. Ying Shi, Haolin Chen, Lantian Li, Zhiyuan Tang, Dong Wang, and Jiqing Han. “Can we trust deep speech prior?” In Proc. 2021 IEEE Spoken Language Technology Workshop (SLT 2021). [arXiv] [IEEE]
  7. Yue Fan, Jiawen Kang, Lantian Li, Kaicheng Li, Haolin Chen, Sitong Cheng, Pengyuan Zhang, Ziya Zhou, Yunqi Cai, and Dong Wang. “CN-CELEB: a challenging Chinese speaker recognition dataset.” In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing 2020 (ICASSP 2020). [arXiv] [IEEE]

Preprints

  1. Haolin Chen and Philip N. Garner. “An investigation into the adaptability of a diffusion-based TTS model” arXiv: 2303.01849. [Link]

Google Scholar