Responsibilities:

-Text To Speech model and performance optimization

-Participate in the development of a large-scale Text To Speech model, including but not limited to optimizing the model structure, pre training ICL, fine-tuning SFT, and other related tasks

-Follow up on cutting-edge technologies related to voice communication

-Participated in the implementation of speech synthesis technology projects for multiple Baidu overseas products

Requirements:

-Master's degree or above, major in computer related field, with experience in speech/signal processing related projects

-More than one year of work experience in the field of speech synthesis -Familiar with Linux and Python, proficient in using deep learning frameworks such as PyTorch

-Good communication, enthusiastic about technology, diligent in learning, positive and proactive

-Bonus points: Published papers in top conferences or journals such as Interspeech and...