High-quality Speech Coding with Sample RNN
Authors:
- 1 May 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7155-7159
Abstract
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 of state-of-the-art classic wide-band codecs. Moreover, it is demonstrated that the proposed scheme can provide a meaningful rate-distortion trade-off without retraining. We evaluate the proposed scheme in a series of listening tests and discuss limitations of the approach.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Spanish Statistical Parametric Speech Synthesis Using a Neural Vocoder2018
- Voice Conversion with Conditional SampleRNN2018
- Wavenet Based Low Rate Speech Coding2018
- Samplernn-Based Neural Vocoder for Statistical Parametric Speech Synthesis2018
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Vector Quantization by Companding a Union of Z-LatticesIEEE Transactions on Information Theory, 2005
- A sinusoidal LPC vocoder2002
- The adaptive multirate wideband speech codec (AMR-WB)IEEE Transactions on Speech and Audio Processing, 2002
- An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network TrajectoriesNeural Computation, 1990
- Efficient vector quantization of LPC parameters at 24 bits/frameThe Journal of the Acoustical Society of America, 1990