🚀 Internship
Research Scientist Intern, Speech Processing
Tencent
3d ago
London
Description
LightSpeed Studios is one of the world’s most innovative and successful game developers. With team across China, United States, Singapore, Canada, United Kingdom, France, Japan, South Korea, New Zealand, and United Arab Emirates. We are expanding to more countries.
Area of Responsibilities
Responsibilities
Your responsibilities include developing novel speech processing algorithms to advance the application of intelligent speech techniches for the gaming/entertainment scenarios, the related fields include but are not limited to, text-to-speech synthesis, singing voice synthesis, voice conversion and speech recognition.
Requirements
1. A minimum of a Master degree in Computer Science, Automation, Pattern Recognition or a related field.
2. Experience in the speech processing or multi-modal processing fields, expertise/deep understanding in at least one specific field such as text-to-speech synthesis, singing voice synthesis, voice conversion, speech recognition and speech recognition.
3. Familiar with Linux, experienced with machine learning/deep-learning algorithms and toolkits (e.g. pytorch/Tensorflow)
Preferred：
1. Strong research background, with a solid publication record on top-tier conferences/journals (Speech related: Interspeech, ICASSP, TASLP, Speech Communication,. etc)
2. Experience in architecting, developing and delivering advanced engineering projects.
3. Passionate and self-motivated.
4. Effective communication skills.