taalua / voice_conversion Goto Github PK

This repo contains the official implementation of the VAE-GAN from the INTERSPEECH 2020 paper Voice Conversion Using Speech-to-Speech Neuro-Style Transfer.

Examples of generated audio using the Flickr8k Audio Corpus: https://ebadawy.github.io/post/speech_style_transfer. Note that these examples are a result of feeding audio reconstructions of this VAE-GAN to an implementation of WaveNet.

Dataset file structure:

/path/to/database
├── spkr_1
│   ├── sample.wav
├── spkr_2
│   ├── sample.wav
│   ...
└── spkr_N
    ├── sample.wav
    ...
# The directory under each speaker cannot be nested.

Note that the number of speakers are currently limited to two. This may extended to an arbitrary amount N in the future.

Here is an example script for setting up data preparation from the Flickr8k Audio Corpus. The speakers of interest are the same as in the paper, but may be modified to other speakers if desirable.

The prepared dataset is organised into a train/eval/test split, the audio is preprocessed and melspectrograms are computed.

python preprocess.py --dataset [path/to/dataset] --test-size [float] --eval-size [float]

The VAE-GAN model uses the melspectrograms to learn style transfer between two speakers.

python train.py --model_name [name of the model] --dataset [path/to/dataset]

By default, the code plots a batch of input and output melspectrograms every epoch. You may add --plot-interval -1 to the above command to disable it. Alternatively you may add --plot-interval 20 to plot every 20 epochs.

By default, models are saved every epoch. With smaller datasets than Flickr8k it may be more appropriate to save less frequently by adding --checkpoint_interval 20 for 20 epochs.

The max number of epochs may be set with --n_epochs. For smaller datasets, you may want to increase this to more than the default 100. To load a pretrained model you can use --epoch and set it to the epoch number of the saved model.

You can access pretrained model files here. By downloading and storing them in a directory src/saved_models/pretrained, you may call it for training or inference with:

--model_name pretrained --epoch 99

Note that for inference the discriminator files D1 and D2 are not required (meanwhile for training further they are). Also here, G1 refers to the decoding generator for speaker 1 (female) and G2 for speaker 2 (male).

The trained VAE-GAN is used for inference on a specified audio file. It works by; sliding a window over a full melspectrogram, locally inferring melspectrogram subsamples, and averaging the overlap.

The script then uses Griffin-Lim to reconstruct audio from the generated melspectrogram. For achieving high quality results like the paper you can feed the reconstructed audio to trained vocoders such as WaveNet.

python inference.py --model_name [name of the model] --epoch [epoch number] --trg_id [id of target generator] --wav [path/to/source_audio.wav]

Instead of a single .wav as input you may specify a whole directory of .wav files by using --wavdir instead of --wav.

By default, plotting input and output melspectrograms is enabled. This is useful for a visual comparison between trained models. To disable set --plot -1

Alongside the process of generating, components for reconstruction and cyclic reconstruction may be enabled by specifying the generator id of the source audio --src_id [id of source generator].

When set, SSIM metrics for reconstructed melspectrograms and cyclically reconstructed melspectrograms are computed and printed at the end of inference.

This is an extra feature to help with comparing the reconstructive capabilities of different models. The higher the SSIM, the higher quality the reconstruction.

• Rewrite preprocess.py to handle:
  • multi-process feature extraction
  • display error messages for failed cases
• Create:
  • requirements.txt
  • Notebook for data visualisation
• Want to add something else? Please feel free to submit a PR with your changes or open an issue for that.

• Real-Time-Voice-Cloning
• UNIT
• wavenet_vocoder
• Flickr8k Audio Corpus

If you find this code useful please cite us in your work:

@inproceedings{AlBadawy2020,
  author={Ehab A. AlBadawy and Siwei Lyu},
  title={{Voice Conversion Using Speech-to-Speech Neuro-Style Transfer}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={4726--4730},
  doi={10.21437/Interspeech.2020-3056},
  url={http://dx.doi.org/10.21437/Interspeech.2020-3056}
}