QMUL, School of Electronic Engineering and Computer Science
Centre for Digital Music Seminar Series
Naoya Takahashi (Sony)
Date/time: Friday 5th February, 10 am – 11 am GMT
Location: Zoom (link to register here)
Title: Audio source separation: Industry No.1 technology and its applications
Abstract: Separating sound sources from a mixture has been one of the most challenging problems in the last decades. Sony is a pioneer in developing deep-learning-based source separation methods, and achieved the best scores in a music source separation challenge, Signal Separation Evaluation Challenge (SiSEC), three times in a row. In this talk, I will present recent advances in audio source separation and its applications in Sony products and services.
Bio: Naoya Takahashi received Ph.D. from University of Tsukuba, Japan, in 2020. From 2015 to 2016, he had worked at the Computer Vision Lab and Speech Processing Group at ETH Zurich as a Visiting Researcher. Since he joined Sony Corporation in 2008, he has performed research in the field of audio, computer vision, and machine learning. In 2018, he won the Sony Outstanding Engineer Award, which is the highest form of individual recognition for Sony Group engineers. His current research activities include audio source separation, voice conversion, video highlight detection, event detection, speech recognition and music technologies.