I’m excited to announce that I’ll be presenting new papers at ICASSP 2023.

Collaborating with my wonderful colleagues on four different projects, including multilingual speech recognition, speech separation, speech restoration, and audio-visual speech synthesis, was an invaluable experience that I cherished.

Here are the accepted papers:

1. Yoohwan Kwon, Soo-Whan Chung, “MoLE: Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition”
   • available on arXiv: https://arxiv.org/abs/2302.13750
2. Jiyoung Lee, Joon Son Chung, Soo-Whan Chung, “Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech”
   • available on arXiv: https://arxiv.org/abs/2302.13700
   • project website: https://facetts.github.io
3. Jaeuk Byun, Youna Ji, Soo-Whan Chung, Soyeon Choe, Min-Seok Choi, “An Empirical Study on Speech Restoration Guided by Self-Supervised Speech Representation”
   • available on arXiv: https://arxiv.org/abs/2305.18739
4. Robin Scheibler, Youna Ji, Soo-Whan Chung, Jaeuk Byun, Soyeon Choe, Min-Seok Choi, “Diffusion-Based Generative Speech Source Separation”
   • available on arXiv: https://arxiv.org/abs/2210.17327

Congratulations to my co-authors for their hard work and dedication.

I am looking forward to meeting you all at ICASSP 2023!