Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Keras implementation of ‘’Deep Speaker: an End-to-End Neural Speaker Embedding System‘’ (speaker recognition)

Companion repository for the paper "A Comparison of Metric Learning Loss Functions for End-to-End Speaker Verification" published at SLSP 2020

Voxceleb1 i-vector based speaker recognition system

Trained speaker embedding deep learning models and evaluation pipelines in pytorch and tesorflow for speaker recognition.

Speaker embedding (d-vector) trained with GE2E loss

Luigi pipeline to download VoxCeleb(2) audio from YouTube and extract speaker segments

DropClass and DropAdapt - repository for the paper accepted to Speaker Odyssey 2020

PyTorch implementation of the 1D-Triplet-CNN neural network model described in Fusing MFCC and LPC Features using 1D Triplet CNN for Speaker Recognition in Severely Degraded Audio Signals by A. Chowdhury, and A. Ross.

PyTorch implementation of Densely Connected Time Delay Neural Network

Create speaker voiceprints from a few seconds of audio. And, identify individuals in real-time streaming or recorded conversations.

simple version of our torch kaldi toolkit, developed at the LIA by 2 apprentices. (@Chaanks & @vbrignatz)

Angular triplet center loss implementation in Pytorch.

PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.