Informatics, TU Vienna

“Towards musical bandwidth expansion using convolutional autoencoders” – Guest Talk

Dr. Matthew Davies (Sound and Music Computing Group, INESC TEC, Portugal) will present a recently developed approach for audio bandwidth extension for music signals using convolutional neural networks (CNNs).

Inspired by the concept of inpainting from the field of image processing, the goal is to reconstruct the high-frequency region (i.e., above a cutoff frequency) of a time-frequency representation given the observation of a band-limited version. The reconstructed time-frequency representation is then inverted using the phase information from the band-limited input to provide an enhanced musical output. The performance of two musically adapted CNN architectures are compared, where each has been trained separately using the STFT and the invertible CQT as input. 

The performance of the proposed approach is demonstrated via the signal to distortion ratio and via a set of audio examples.

Biography

Matthew Davies is a music information retrieval researcher with a background in digital signal processing, and currently holds an FCT Investigator Development Grant. His main research interests include the analysis of rhythm in musical audio signals, evaluation methodology, creative music applications, and reproducible research. Since 2014, Matthew has coordinated the Sound and Music Computing Group in the Centre for Telecommunications and Multimedia at INESC TEC. He is an Associate Editor for the IEEE/ACM Transactions on Audio, Speech and Language Processing and coordinated the 4th Annual IEEE Signal Processing Cup. He was a keynote speaker at the 16th Rhythm Production and Perception Workshop, and General Chair of the 13th International Symposium on Computer Music Multidisciplinary Research.