andi611/cs-tacotron-pytorch

Pytorch implementation of CS-Tacotron, a code-switching speech synthesis end-to-end generative TTS model.

Hello 👋

My name is Andy T. Liu. I received my Ph.D. degree in the College of Electrical Engineering & Computer Science (EECS) from the National Taiwan University (NTU), Taipei, Taiwan, in 2024, supervised by Professor Hung-Yi Lee. I’m from the “Speech Processing and Machine Learning” laboratory at NTU, also working with Professor Lin-shan Lee.

I offer more than five years of dedicated experience in machine learning, self-supervised learning, foundation models, and generative models for speech and NLP.

My scholarly impact is affirmed by over 1,500 citations and an h-index of 12 on Google Scholar. The IEEE Signal Processing Society has identified one of my publications, “TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech”, as one of the top 25 downloaded articles from Sept. 2021 - Sept. 2022 for IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP) on IEEE Xplore®.

My colleague Shu-wen (Leo) Yang and I founded the S3PRL Toolkit in 2019 – now celebrated with over 2,000 stars on GitHub – and have kept developing ever since. Our S3PRL Toolkit provides an easy-to-use interface to the research community, including self-supervised foundation models and downstream tasks.

• 👯 I’m looking to: collaborate on more research projects!
• 😄 Pronouns: He/Him
• ⚡ Fun fact: I am also a qualified PADI Scuba diving instructor 🤿
• 📫 Visit my website to see more:

https://andi611.github.io/

cs-tacotron-pytorch's Issues

cudnn cudatoollkit 版本问题