I am a Ph.D. student in Speech Processing and Machine Learning Lab at National Taiwan University (NTU) advised by Prof. Hung-yi Lee, Prof. Shang-Tse Chen.
I am passionate about exploring the use of synthetically generated speech and text to bridge gaps in model performance across diverse domains, particularly when real data is scarce or biased.
This includes investigating the efficacy of synthetic-to-real transfer for speech recognition in underrepresented or atypical domains, and addressing issues like gender bias in large language models.
Besides, I loves to take photos of the sea, streets, and people, check the photos here!
I am passionate about exploring the use of synthetically generated speech and text to bridge gaps in model performance across diverse domains, particularly when real data is scarce or biased.
This includes investigating the efficacy of synthetic-to-real transfer for speech recognition in underrepresented or atypical domains, and addressing issues like gender bias in large language models.
Besides, I loves to take photos of the sea, streets, and people, check the photos here!
