Publication Date: 2023/08/08
Abstract: Voice technology has emerged as a hotspot for deep learning research due to fast advancements in computer technology. The goal of human-computer interaction should be to give computers the ability to feel, see, hear, and speak. Voice is the most favorable approach for future interactions between humans and computers because it offers more benefits than any other method. One example of voice technology that is capable of imitating a particular person's voice is voice cloning. Real-time voice cloning with only a few samples is proposed as a solution to the issue of having to provide a large amount of samples and having to endure a long time in the past for voice cloning. This strategy deviates from the conventional model. For independent training, different databases and models are used but for joint modeling, only three models are used. The vocoder makes use of a novel type of LPCNET that works well on certain samples and low- performance devices.
Keywords: Real-Time, Samples, Voice Cloning.
DOI: https://doi.org/10.5281/zenodo.8224163
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23JUL1648.pdf
REFERENCES