3 papers
eess.AS2020
Source coding of audio signals with a generative model
Roy Fejgin, Janusz Klejsa, Lars Villemoes +1
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.…
eess.AS2018
High-quality speech coding with SampleRNN
Janusz Klejsa, Per Hedelin, Cong Zhou +2
We provide a speech coding scheme employing a generative model based on SampleRNN that, while operating at significantly lower bitrates, matches or surpasses the perceptual quality…
cs.SD2018
Voice Conversion with Conditional SampleRNN
Cong Zhou, Michael Horgan, Vivek Kumar +2
Here we present a novel approach to conditioning the SampleRNN generative model for voice conversion (VC). Conventional methods for VC modify the perceived speaker identity by conv…