Waveform generator based on signal reshaping for statistical parametric speech synthesis.
This software is based on the work presented at Interspeech 2016:
More information athttp://felipeespic /wavgensr/
@author:Felipe Espic
This software generates speech waveforms from the speech features:
- Spectral envelope
- F0 contour
,which may be extracted by a vocoder (e.g., STRAIGHT, WORLD) or generated by an acoustic model (e.g., Merlin, HTS).
Key points:
- No need of aperiodicities.
- No minimum phase assumtion.
- Natural phase spectrum plus periodic and aperiodic components given "for free" by natural speech recordings.
See the LICENCE file for details.
- OS: Linux (not tested in other OS's yet)
- MATLAB (Any modern version)
Just download and compile SPTK by:
cd tools
./download_and_compile_sptk.sh
This will compile SPTK automatically for you.
Just go to/demos
,read the instructions in theWavGenSR_demo.m
script, and run it using MATLAB.
You will lern very quickly how to use the main functionWavGenSR
by this simple demo.
Then, if wanted you can modifyWavGenSR_demo.m
to suit your needs.