腾讯-研究实习生 （演讲）

工作内容：

1.Responsible for the research and development of algorithms and models for speech recognition, speech synthesis, and speech cloning in minor languages, including but not limited to the implementation and improvement of acoustic models, vocoder algorithms, and their optimization in real-world scenarios.

2.Keep up with cutting-edge technology research, integrating business planning to continuously explore innovations in speech synthesis technology and application scenarios.

3.Apply relevant algorithmic results to various scenarios such as speech, speech translation (S2TT, S2ST), and virtual humans.

岗位要求：

1.Research and work experience in speech synthesis or speech cloning, with a background in speech, signal processing, computer science, or related fields.

2.Master's or PhD in Computer Science, Computational Linguistics, Artificial Intelligence, or related fields.

3.Deep understanding of TTS and speech cloning principles, mastery of the latest speech technology, and extensive involvement in the development and implementation of cutting-edge speech synthesis or speech cloning algorithms.

4.Experience in high-expressiveness speech synthesis, style transfer, voice conversion, and emotional synthesis is preferred.

5.Proficient in deep learning, neural networks, and related open-source tools and frameworks (such as TensorFlow, PyTorch).

6.Strong logical thinking, excellent analytical and communication skills, high enthusiasm for technology, self-driven, and pursuit of excellence.

7.Strong team collaboration and communication skills, able to work closely with team members to drive project progress.

8.Passionate about the gaming industry with a certain level of understanding of the gaming field.