PyTorch implementation of the method described in the Voice Synthesis for in-the-Wild Speakers via a Phonological Loop.

VoiceLoop is a neural text-to-speech (TTS) that is able to transform text to speech in voices that are sampled in the wild. Some demo samples can be found here.

• Demo Samples (Updated 10/25/2017)
• Quick Start
• Setup
• Training

Follow the instructions in Setup and then simply execute:

python generate.py  --npz data/vctk/numpy_features_valid/p318_212.npz --spkr 13 --checkpoint models/vctk/bestmodel.pth

Results will be placed in models/vctk/results. It will generate 2 samples:

• The generated sample will be saved with the gen_10.wav extension.
• Its ground-truth (test) sample is also generated and is saved with the orig.wav extension.

You can also generate the same text but with a different speaker, specifically:

python generate.py  --npz data/vctk/numpy_features_valid/p318_212.npz --spkr 18 --checkpoint models/vctk/bestmodel.pth

Which will generate the following sample.

Here is the corresponding attention plot:

Legend: X-axis is output time (acoustic samples) Y-axis is input (text/phonemes). Left figure is speaker 10, right is speaker 14.

Finally, free text is also supported:

python generate.py  --text "hello world" --spkr 1 --checkpoint models/vctk/bestmodel.pth

Requirements: Linux/OSX, Python2.7 and PyTorch 0.1.12. The current version of the code requires CUDA support for training. Generation can be done on the CPU.

git clone https://github.com/facebookresearch/loop.git
cd loop
pip install -r scripts/requirements.txt

The data used to train the models in the paper can be downloaded via:

bash scripts/download_data.sh

The script downloads and preprocesses a subset of VCTK. This subset contains speakers with american accent.

The dataset was preprocessed using Merlin - from each audio clip we extracted vocoder features using the WORLD vocoder. After downloading, the dataset will be located under subfolder data as follows:

loop
├── data
    └── vctk
        ├── norm_info
        │   ├── norm.dat
        ├── numpy_feautres
        │   ├── p294_001.npz
        │   ├── p294_002.npz
        │   └── ...
        └── numpy_features_valid

The preprocess pipeline can be executed using the following script by Kyle Kastner: https://gist.github.com/kastnerkyle/cc0ac48d34860c5bb3f9112f4d9a0300.

Pretrainde models can be downloaded via:

bash scripts/download_models.sh

After downloading, the models will be located under subfolder models as follows:

loop
├── data
├── models
    ├── vctk
    │   ├── args.pth
    │   └── bestmodel.pth
    └── vctk_alt

Update 10/25/2017: Single speaker model coming soon

Finally, speech generation requires SPTK3.9 and WORLD vocoder as done in Merlin. To download the executables:

bash scripts/download_tools.sh

Which results the following sub directories:

loop
├── data
├── models
├── tools
    ├── SPTK-3.9
    └── WORLD

Training a new model on vctk, first train the model using noise level of 4 and input sequence length of 100:

python train.py --expName vctk --data data/vctk --noise 4 --seq-len 100 --epochs 90

Then, continue training the model using noise level of 2, on full sequences:

python train.py --expName vctk_noise_2 --data data/vctk --checkpoint checkpoints/vctk/bestmodel.pth --noise 2 --seq-len 1000 --epochs 90

If you find this code useful in your research then please cite:

@article{taigman2017voice,
  title           = {Voice Synthesis for in-the-Wild Speakers via a Phonological Loop},
  author          = {Taigman, Yaniv and Wolf, Lior and Polyak, Adam and Nachmani, Eliya},
  journal         = {ArXiv e-prints},
  archivePrefix   = "arXiv",
  eprinttype      = {arxiv},
  eprint          = {1705.03122},
  primaryClass    = "cs.CL",
  year            = {2017}
  month           = July,
}

Loop has a CC-BY-NC license.