search

asteroid-team / torch-audiomentations

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
MIT License
926 stars 87 forks source link

Implement Vocal Tract Length Perturbation #115

Open akashrajkn opened 2 years ago

akashrajkn commented 2 years ago

It was introduced here: https://arxiv.org/pdf/2011.12536.pdf VTLP is used in speech recognition (https://arxiv.org/pdf/2201.05562.pdf, http://www.cs.toronto.edu/~hinton/absps/perturb.pdf)

Reference code for vtlp is available here: https://github.com/makcedward/nlpaug/blob/master/nlpaug/model/audio/vtlp.py

iver56 commented 2 years ago

Interesting!