Improving the Efficiency of Dysarthria Voice Conversion System by the Data Augmentation Approach
The DVC 3.1 system adopts text-to-speech (text-to-speech) and multi-domain speech conversion models to synthesize large sets of similar speech to patients’ and target speakers’ speech, and furthermore, exploits phonetic posteriorgrams (PPGs) and Gated CNN models to perform the voice conversion for patient＇s voice characteristics. Finally, take advantage of WaveGlow vocoder to convert the converted features into speech for the listener to listen.
Healthy diet for elderly: Improvement muscle texture of pork loin by the combination of kiwifruit powder and sous-vide cooking
A Study on the Development of a Mixed Reality System Applied to the Practice of Socially Interactive Behaviors of Children with Autism Spectrum Disorder
-.png)
An Artificial Intelligence Medicine Recognition and Verification System in Hospital Dispensing Room
Development of AI assisted assessment and intervention system based on the culture contextualization for care of people with neurocognitive disoder.
Technology maturity：Prototype
Exhibiting purpose：Display of scientific results
Trading preferences：Technical license/cooperation、Negotiate by self
Coming soon!