Description:You will work with a small team of robotic perception experts to drive the development of robot software modules that focus on estimating user and environment state from audio and video data. These modules will run on embedded compute platforms supporting Client real-time social robotics applications. Software modules may include:
- Detecting audio and vision based human communication signals
- Prosody analysis
- Multimodal user recognition
- Sound localization
- Recognition of common environmental sounds
- Integration and testing of automatic speech recognition with visual perception systems
Necessary Qualifications:Master's degrees with at least 3 years' work experience or a PhD. Candidates with PhD strongly preferred.
Experience applying computer vision to sensing humans
Experience with real-time audio processing
Experience in real-time analysis of human speech
C++, Java, Python, Android
Nice to haveExperience in robotics
Experience with applying machine learning to sensing tasks
Mandarin
