Voice Cloning Optimization

An artificial intelligence tool that is capable of generating natural-sounding speech can be embedded into many valuable services such as conversational agents for the disabled and conversational assistants. Such tool, when equipped with the capability of mimicking individuals vocal characteristics, will improve personalization of these services. In this project the intern will seek to develop a state-of-the-art voice cloning model. The two major research agendas underlying this project are as follow: to develop a data-efficient voice cloning model with high speech synthesis quality; to enrich voice cloning models with the capacity of voice properties manipulation for speech synthesis. On the former agenda the intern will set out to develop a model that requires minimal fine-tuning to pick up a new speakers vocal characteristics and use them to generate realistic audio samples. TO BE CONT’D

Faculty Supervisor:

David Duvenaud

Student:

Wei Zhen Teoh

Partner:

Lyrebird AI

Discipline:

Computer science

Sector:

Information and communications technologies

University:

Program: