2026-09-20T17:56:33Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/100932 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Do, Minh N. Lim, Teck Yian 2018-09-04T20:26:52Z 2018-09-04T20:26:52Z 2018-04-23 2018-05 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. Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-08-31 without embargo terms The student, Teck Yian Lim, accepted the attached license on 2018-04-23 at 11:33. The student, Teck Yian Lim, submitted this Thesis for approval on 2018-04-23 at 11:36. This Thesis was approved for publication on 2018-04-23 at 12:23. DSpace SAF Submission Ingestion Package generated from Vireo submission #12134 on 2018-08-31 at 17:10:54 Made available in DSpace on 2018-09-04T20:26:52Z (GMT). No. of bitstreams: 2 LIM-THESIS-2018.pdf: 11597324 bytes, checksum: 04f5a5cf48e0be1dfd233720869c932c (MD5) LICENSE.txt: 4210 bytes, checksum: 7f5b4ca9d074e40fa324580dcad4ed15 (MD5) Previous issue date: 2018-04-23 application/pdf http://hdl.handle.net/2142/100932 en Copyright 2018 Teck Yian Lim Deep Neural Networks Audio Signal Processing Generative Adversarial Networks GAN DNN Super resolution Audio super-resolution with deep neural networks text text Electrical & Computer Eng Electrical & Computer Engr University of Illinois at Urbana-Champaign Thesis M.S.