cvqluu/MTL-Speaker-Embeddings cvqluu/MTL-Speaker-Embeddings

  • Stars
    star
    24
  • Rank 986,245 (Top 20 %)
  • Language
    Python
  • License
    MIT License
  • Created about 4 years ago
  • Updated about 2 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
cvqluu/MTL-Speaker-Embeddings
github

cvqluu

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Code for the paper: "Leveraging speaker attribute information using multi task learning for speaker verification and diarization" presented at Interspeech 2021

More Repositories

1

Angular-Penalty-Softmax-Losses-Pytorch

Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)
Python
474
star
2

TDNN

Time delay neural network (TDNN) implementation in Pytorch using unfold method
Python
189
star
3

Factorized-TDNN

PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi
Python
140
star
4

simple_diarizer

Simplified diarization pipeline using some pretrained models - audio file to diarized segments in a few lines of code
Python
125
star
5

GE2E-Loss

Pytorch implementation of Generalized End-to-End Loss for speaker verification
Python
79
star
6

nn-similarity-diarization

Neural network based similarity scoring for diarization (pytorch implementation of "LSTM based Similarity Measurement with Spectral Clustering for Speaker Diarization")
Python
41
star
7

dropclass_speaker

DropClass and DropAdapt - repository for the paper accepted to Speaker Odyssey 2020
Python
21
star
8

splitdim_disentangle

Disentangling speaker embeddings using multi-task learning and adversarial training
Python
7
star