Audio super-resolution with deep neural networks

Deep Neural Networks;Audio;Signal Processing;Generative Adversarial Networks;GAN;DNN;Super resolution

Lim, Teck Yian ; Do ; Minh N.

关键词: Deep Neural Networks;    Audio;    Signal Processing;    Generative Adversarial Networks;    GAN;    DNN;    Super resolution;   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/100932/LIM-THESIS-2018.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

This thesis reports various attempts at applying generative deep neural networks to audio for the task of recovering a high quality audio signal when given a low sample rate signal. Our experiments show that deep networks are able to discover patterns in speech and music signals by working in both time and frequency domains jointly. Such a network structure outperforms other methods that work either in the time domain or frequency domain exclusively. In our evaluations with speech signals, our method outperforms a time-domain only method by Kuleshov et. al. by 1.4 dB for 4x and by up to 2.0 dB for 8x upsampling.