-
Audio Intelligence Technology & Research Lab
- Research theme:
Speech Enhancement, Audio coding,
Speech & Sound Recognition, 3D Audio -
Speech enhancement and audio coding
- Improving speech quality and
analysis/synthesis audio signal -
Speech and sound recognition
- Transcription spoken languages into readable text and classification sound event
-
3D audio
- Mimicking natural sound to feel like in 3D space
-
Climate change prediction
- Prediction climate change based on neural networks
-
Open database and software
- Noisy speech data in drone environment
- Deep learning based violence detection
-
Speech enhancement & audio coding
- Improving speech quality and pre-processing for speech recognition by reduction background noise, reverberation and distortion.
- Audio coding type detection and parameter reconstruction for synthetic speech quality enhancement.
-
Speech and Sound recognition
- Speech recognition is the technologies that transcript spoken languages into readable text in real time.
- Sound event classification is identifying the rare sound events, scream, gun shot, glass-breaking, etc. for security event detection.
-
3D audio
- Spatial domain convolution of sound waves using Head-related transfer functions.
- Phenomenon of transforming sound waves to mimic natural sounds waves, which emanate from a point in a 3D space.
-
Climate change prediction
- monitoring and understanding for climate prediction of man-made climate change.
- air quality forecasting modeling based deep neural networks.
- prediction on changes of aerosol on earth environment.