LPCNet icon indicating copy to clipboard operation
LPCNet copied to clipboard

Efficient neural speech synthesis

Results 12 LPCNet issues
Sort by recently updated
recently updated
newest added

Hi,MIWoo, Did you tried the new version LPCNet which employ quanlization for GRU? [https://github.com/xiph/LPCNet](url).

@MlWoo Hi, I use LPCNet as vocoder to train female and male dataset seperately. The synthesized voice of female is OK, but the synthesized voice of male trembles. Have you...

In the ReadMe, it's mentioned > Convert the data generated at the last step which has .f32 extension to what could be loaded with numpy. I merge it to the...

> Synthesis the waveform using LPCNet You should use LPCNet of the C code version and make sure that the LPCNet is builded with TACOTRON2 Macro. @MlWoo what changes will...

Can we change LPCNet for 80 mels , so that any of the mel generator Tacontr2 , Fastspeech can be directly use without retraining. Any idea what changes might be...

Hi, all, I had trained lpcnet model and compile the execution file from test_lpcnet.c, synthetise with it is not quick enough. Statistically we cost about 1 seconds to synthetize a...

the extra feature for tacotron were found by hard writting in 'dump_data.c' line 142 & 143. > features[NB_BANDS] -= 1.3; > features[NB_BANDS+1] -= 0.9; What means of them and How...

@MlWoo have you tried Fastspeech for Mel generation , its astonishing fast for generating Mel spectrograms, combined with LPCNET vocoder it could be work as realtime voice synthesis.

Hello, MIWoo,thanks for your improvement of the training Tacotron and LPCnet. But i find that the synthesis results are not same with python (test_lpcnet.py) and c (lpcnet.c) Do i make...

I have run the preprocessing steps on MacOS and run the LPCNet training and everything was good and output waves are very clean. However, following the same steps on Ubuntu...