Sorry, you need to enable JavaScript to visit this website.

Source Coding of Audio Signals with a Generative Model

Citation Author(s):
Roy Fejgin, Janusz Klejsa, Lars Villemoes, Cong Zhou
Submitted by:
Lars Villemoes
Last updated:
14 April 2020 - 5:16am
Document Type:
Document Year:
Roy Fejgin
Paper Code:

We consider source coding of audio signals with the help of a generative model. We use a construction where a waveform is first quantized, yielding a finite bitrate representation. The waveform is then reconstructed by random sampling from a model conditioned on the quantized waveform. The proposed coding scheme is theoretically analyzed. Using SampleRNN as the generative model, we demonstrate that the proposed coding structure provides performance competitive with state-of-the-art source coding tools for specific categories of audio signals.

0 users have voted:


This is an audio demo