Audio AI research awarded the best paper award
IEEE Signal Processing Society has granted the 2024 best paper award for the paper “Deep Learning for Audio Signal Processing”, authored by Hendrik Purwins, Bo Li, Tuomas Virtanen, Jan Schlüter, Shuo-Yiin Chang, and Tara Sainath.
The article presents deep neural network based methods for a wide range of audio and speech tasks, including audio and speech recognition, synthesis, and processing. These methods have become the cornerstone of modern AI-based audio-processing techniques, which are very widely used in the academic and industry. In more general, deep neural networks have had a fundamental role in the recent AI boom, since they enable complex tasks which is not possible with conventional methods.
Tuomas Virtanen is a professor on signal processing at Tampere University, Signal Processing Research Center, where he is leading the Audio Research Group. Virtanen is teaching Deep Learning course at Tampere University which covers the fundamentals of deep neural networks. Virtanen was among the first researchers at Tampere University to start research on deep learning in 2013. Hendrik Purwins is working at Accenture, Bo Li, Shuo-Yiin Chang, and Tara Sainath at Google DeepMind, and Jan Schlüter at Johannes Kepler University Linz.
The Institute of Electrical and Electronics Engineers (IEEE) is a professional association covering a wide range of engineering fields which has 460 000 members. The IEEE’s first society, the Signal Processing Society is the world’s premier professional society for signal processing scientists and professionals since 1948, and has more than 20 000 members.
