Starred repositories
18
results
for source starred repositories
Clear filter
In defence of metric learning for speaker recognition
A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR
Collection of audio-focused loss functions in PyTorch
An invertible and differentiable implementation of the Constant-Q Transform (CQT).
PESQ (Perceptual Evaluation of Speech Quality) Wrapper for Python Users (narrow band and wide band)
A high-level toolbox for using complex valued neural networks in PyTorch
Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing
Quadruped Trajectory Optimization Stack (QTOS) is an optimization framework for legged locomotion that autonomously generates full-body trajectory plans across challenging terrains.
This repository is to prepare for Machine Learning interviews.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
This repository includes the code to reproduce our paper "Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation".
Utterance-level Aggregation For Speaker Recognition In The Wild
Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)
This is the Python code to test Deep4SNet. This allows you to classify both original and fake voice recordings. Authors: Dora Maria Ballesteros, Yohanna Patricia Rodriguez, Diego Renza, Gonzalo Arce
Implementation of the Sliced Wasserstein Autoencoders