Documents
Poster
WAVENET BASED LOW RATE SPEECH CODING
![](https://sigport.org/sites/default/files/styles/home/public/ICASSP_2018_docs.jpg?itok=gxiDHw0M)
- Citation Author(s):
- Submitted by:
- Quan Wang
- Last updated:
- 4 May 2018 - 2:28pm
- Document Type:
- Poster
- Document Year:
- 2018
- Event:
- Presenters:
- W. Bastiaan Kleijn
- Paper Code:
- AASP-P10
- Categories:
- Log in to post comments
Traditional parametric coding of speech facilitates low rate but provides poor reconstruction quality because of the inadequacy of the model used. We describe how a WaveNet generative speech model can be used to generate high quality speech from the bit stream of a standard parametric coder operating at 2.4 kb/s. We compare this parametric coder with a waveform coder based on the same generative model and show that approximating the signal waveform incurs a large rate penalty. Our experiments confirm the high performance of the WaveNet based coder and show that the speech produced by the system is able to additionally perform implicit bandwidth extension and does not significantly impair recognition of the original speaker for the human listener, even when that speaker has not been used during the training of the generative model.