Fu Qiang is a researcher at the Alibaba DAMO Academy’s Speech Lab. He holds a Ph.D. from the Xidian University and later worked as a postdoctoral researcher at leading speech recognition research institutions, including OGI in the United States. He also worked as a researcher at the Institute of Acoustics of the Chinese Academy of Sciences. Dr. Fu has published nearly 100 papers in authoritative academic journals and conferences, both domestically and internationally, holds more than 10 patents for proprietary technology and presided over the development of a national standards of speech recognition. In 2014, he won the Outstanding Science and Technology Achievement Award from the Chinese Academy of Sciences, and in 2016, he won the Outstanding Person Award from the Speech Industry Alliance of China.
Track: Audio Experience
2019/08/24 09:30 - 18:10
Topics in the track
This talk will cover various topics on immersive audio, mainly object audio and ambisonics. I will describe some algorithms, software, and hardware for soundfield capture, transmission, and rendering. Use cases in entertainment, VR, audio conferencing will be touched upon briefly. The intended audience include those working on audio algorithms, content creation, and immersive audio product design.
For fans and practitioners in the fields of artificial intelligence, biometrics, and identity authentication. We mainly introduce the basic concepts and methods in speaker recognition, as well as the countermeasures for replay attacks. Listeners can learn about the basic principles of speaker recognition, lay the foundation for building a speaker recognition system.
Immersive and interactive audio is about to be introduced for 4k and 8K television around the globe. In addition to the improved listening experience, it comes with support for multiple languages and the possibility for users to adjust the sound to their liking. The presentation explains how content streaming providers can make use of these advanced features in OTT services.