Real-Time Talking Avatar on the Internet Using Kinect and Voice Conversion
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2015, Vol 6, Issue 12
Abstract
We have more chances to communicate via the in-ternet. We often use text/video chat, but there are some problems, such as a lack of communication and anonymity. In this paper, we propose and implement a real-time talking avatar, where we can communicate with each other by synchronizing character’s voice and motion from ours while keeping anonymity by using a voice conversion technique. For the voice conversion, we improve accuracy of the voice conversion by specializing to the target character’s voice. Finally, we conduct subjective experiments and show the possibility of a new style of communication on the internet.
Authors and Affiliations
Takashi Nose, Yuki Igarashi
Keywords
Related Articles
- EP ID EP133190
- DOI 10.14569/IJACSA.2015.061240
- Views 145
- Downloads 0
A new Hierarchical Group Key Management based on Clustering Scheme for Mobile Ad Hoc Networks
The migration from wired network to wireless network has been a global trend in the past few decades because they provide anytime-anywhere networking services. The wireless networks are rapidly deployed in the future, se...
Applied Artificial Intelligence in 3D-game (HYSTERIA) using UNREAL ENGINE4
Game development industry spreading it roots at wider level. With the advancements in gaming technologies industries adopted latest trends for developing modern games. Artificial intelligence (AI) with programming provid...
e-Learning Proposal Supported by Reasoning based on Instances of Learning Objects
In recent years, new research has appeared in the area of education, which has focused on the use of information technology and the Internet to promote online learning, breaking many barriers of traditional education suc...
Hybrid Denoising Method for Removal of Mixed Noise in Medical Images
Nowadays, Digital image acquisition and processing techniques plays a very important role in current day medical diagnosis. During the acquisition process, there could be distortions in the images, which will negat...
Efficient Feature Selection for Product Labeling over Unstructured Data
The paper introduces a novel feature selection algorithm for labeling identical products collected from online web resources. Product labeling is important for clustering similar or same products. Products blindly crawle...