Baseline for the Spoofing-aware Speaker Verification Challenge 2022

Last update: Dec 28, 2022

Related tags

Deep Learning SASVC2022_Baseline

Overview

Introduction

This repository contains several materials that supplements the Spoofing-Aware Speaker Verification (SASV) Challenge 2022 including:

calculating metrics;
extracting speaker/spoofing embeddings from pre-trained models;
training/evaluating Baseline2 in the evaluation plan.

More information can be found in the webpage and the evaluation plan

Prerequisites

Load ECAPA-TDNN & AASIST repositories

git submodule init
git submodule update

Install requirements

pip install -r requirements.txt

Data preparation

The ASVspoof2019 LA dataset [1] can be downloaded using the scipt in AASIST [2] repository

python ./aasist/download_dataset.py

Speaker & spoofing embedding extraction

Speaker embeddings and spoofing embeddings can be extracted using below script. Extracted embeddings will be saved in ./embeddings.

Speaker embeddings are extracted using the ECAPA-TDNN [3].
- Implmented by https://github.com/TaoRuijie/ECAPATDNN
Spoofing embeddings are extracted using the AASIST [2].
We also prepared extracted embeddings.
- To use prepared emebddings, git-lfs is required. Please refer to https://git-lfs.github.com for further instruction. After installing git-lfs use following command to download the embeddings.
```
git-lfs install
git-lfs pull
```

python save_embeddings.py

Baseline 2 Training

Run below script to train Baseline2 in the evaluation plan.

It will reproduce Baseline2 described in the Evaluation plan.

python main.py --config ./configs/baseline2.conf

Developing own models

Currently adding...

Adding custom DNN architecture

create new file under ./models/.
create a new configuration file under ./configs
in the new configuration, modify model_arch and add required arguments in model_config.
run python main.py --config {USER_CONFIG_FILE}

Using only metrics

Use get_all_EERs in metrics.py to calculate all three EERs.

prediction scores and keys should be passed on using
- protocols/ASVspoof2019.LA.asv.dev.gi.trl.txt or
- protocols/ASVspoof2019.LA.asv.eval.gi.trl.txt

References

[1] ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech

@article{wang2020asvspoof,
  title={ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech},
  author={Wang, Xin and Yamagishi, Junichi and Todisco, Massimiliano and Delgado, H{\'e}ctor and Nautsch, Andreas and Evans, Nicholas and Sahidullah, Md and Vestman, Ville and Kinnunen, Tomi and Lee, Kong Aik and others},
  journal={Computer Speech \& Language},
  volume={64},
  pages={101114},
  year={2020},
  publisher={Elsevier}
}

[2] AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks

@inproceedings{Jung2022AASIST,
  author={Jung, Jee-weon and Heo, Hee-Soo and Tak, Hemlata and Shim, Hye-jin and Chung, Joon Son and Lee, Bong-Jin and Yu, Ha-Jin and Evans, Nicholas},
  booktitle={Proc. ICASSP}, 
  title={AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks}, 
  year={2022}

[3] ECAPA-TDNN: Emphasized Channel Attention, propagation and aggregation in TDNN based speaker verification

@inproceedings{desplanques2020ecapa,
  title={{ECAPA-TDNN: Emphasized Channel Attention, propagation and aggregation in TDNN based speaker verification}},
  author={Desplanques, Brecht and Thienpondt, Jenthe and Demuynck, Kris},
  booktitle={Proc. Interspeech 2020},
  pages={3830--3834},
  year={2020}
}

Official PyTorch implementation of "AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks"

AASIST This repository provides the overall framework for training and evaluating audio anti-spoofing systems proposed in 'AASIST: Audio Anti-Spoofing

56 Jan 2, 2023

Using LSTM to detect spoofing attacks in an Air-Ground network

Using LSTM to detect spoofing attacks in an Air-Ground network Specifications IDE: Spider Packages: Tensorflow 2.1.0 Keras NumPy Scikit-learn Matplotl

1 Nov 20, 2021

Flexible-Modal Face Anti-Spoofing: A Benchmark

Flexible-Modal FAS This is the official repository of "Flexible-Modal Face Anti-

22 Nov 10, 2022

Imposter-detector-2022 - HackED 2022 Team 3IQ - 2022 Imposter Detector

HackED 2022 Team 3IQ - 2022 Imposter Detector By Aneeljyot Alagh, Curtis Kan, Jo

3 Aug 20, 2022

ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge (ManiSkill Challenge), a large-scale learning-from-demonstrations benchmark for object manipulation.

ManiSkill-Learn ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge, a large-scale learning-from-dem

48 Dec 30, 2022

Contrastive Fact Verification

VitaminC This repository contains the dataset and models for the NAACL 2021 paper: Get Your Vitamin C! Robust Fact Verification with Contrastive Evide

47 Dec 19, 2022

Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"

Zero-shot-Fact-Verification-by-Claim-Generation This repository contains code and models for the paper: Zero-shot Fact Verification by Claim Generatio

47 Jan 1, 2023

The VeriNet toolkit for verification of neural networks

VeriNet The VeriNet toolkit is a state-of-the-art sound and complete symbolic interval propagation based toolkit for verification of neural networks.

9 Dec 21, 2022

Pocsploit is a lightweight, flexible and novel open source poc verification framework

208 Dec 24, 2022

Comments

About the extracted embeddings.

When we installed the git-lfs and step to pull the embeddings data, an error like:

batch response: This repository is over its data quota. Account responsible for LFS bandwidth should purchase more data packs to restore access.
error: failed to fetch some objects from 'https://github.com/sasv-challenge/SASVC2022_Baseline.git/info/lfs

was appeared.

What should I do? How can I download the embeddings data?

opened by ikou-austin 3

Reproducing baseline1

Thanks for providing the code for pre-trained models and baseline2. I am reproducing baseline1 based on your description in the evaluation plan, but I got very different results on the development set. I am also curious why the SPF-EER on the development set is much worse than that on the evaluation set in your results. Could you please provide the code for reproducing your baseline1 result? Thank you so much!

opened by yzyouzhang 3
omegaconf.errors.ConfigAttributeError: Missing key

I encounter the following error when I run main.py with the Baseline2 configuration.

omegaconf.errors.ConfigAttributeError: Missing key

There are in total three keys missing. min_req_mem gradient_clip reload_every_n_epoch

I fixed these missing keys one by one by setting them to 0 or None. I am curious what are the default values for these. Thank you very much.

opened by yzyouzhang 3
speaker_loss.weight is not in the model.

Thanks for your repo. I have successfully replicated the baseline2 performance. I encounter the following messages when I run python save_embeddings.py. It did not crash the program but I wonder where is the second line printed from since I did not find it. I am also not sure if it will cause potential issues.

Device: cuda speaker_loss.weight is not in the model. Getting embedgins from set trn...

Thanks.

opened by yzyouzhang 1

Releases(v0.0.2)

v0.0.2(Jan 23, 2022)
Major update

PyTorchLightning usage

Code refactoring

Extracted embedding support

Readme, guide updated

Metric as independent function

Source code(tar.gz)
Source code(zip)
v0.0.1(Jan 14, 2022)

Initial working version.

By Hye-jin Shim
Source code(tar.gz)
Source code(zip)

Owner

GitHub Repository

(ICCV 2021) ProHMR - Probabilistic Modeling for Human Mesh Recovery

ProHMR - Probabilistic Modeling for Human Mesh Recovery Code repository for the paper: Probabilistic Modeling for Human Mesh Recovery Nikos Kolotouros

209 Dec 13, 2022

A Simplied Framework of GAN Inversion

Framework of GAN Inversion Introcuction You can implement your own inversion idea using our repo. We offer a full range of tuning settings (in hparams

13 Sep 27, 2022

EMNLP 2021 paper Models and Datasets for Cross-Lingual Summarisation.

This repository contains data and code for our EMNLP 2021 paper Models and Datasets for Cross-Lingual Summarisation. Please contact me at

9 Oct 28, 2022

Attack on Confidence Estimation algorithm from the paper "Disrupting Deep Uncertainty Estimation Without Harming Accuracy"

Attack on Confidence Estimation (ACE) This repository is the official implementation of "Disrupting Deep Uncertainty Estimation Without Harming Accura

3 Mar 30, 2022

《LXMERT: Learning Cross-Modality Encoder Representations from Transformers》(EMNLP 2020)

The Most Important Thing. Our code is developed based on: LXMERT: Learning Cross-Modality Encoder Representations from Transformers

53 Dec 16, 2022

Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

Text-AutoAugment (TAA) This repository contains the code for our paper Text AutoAugment: Learning Compositional Augmentation Policy for Text Classific

105 Jan 03, 2023

Baseline for the Spoofing-aware Speaker Verification Challenge 2022

Related tags

Overview

Introduction

Prerequisites

Load ECAPA-TDNN & AASIST repositories

Install requirements

Data preparation

Speaker & spoofing embedding extraction

Baseline 2 Training

Developing own models

Adding custom DNN architecture

Using only metrics

References

You might also like...

Official PyTorch implementation of "AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks"

Using LSTM to detect spoofing attacks in an Air-Ground network

Flexible-Modal Face Anti-Spoofing: A Benchmark

Imposter-detector-2022 - HackED 2022 Team 3IQ - 2022 Imposter Detector

ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge (ManiSkill Challenge), a large-scale learning-from-demonstrations benchmark for object manipulation.

Contrastive Fact Verification

Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"

The VeriNet toolkit for verification of neural networks

Pocsploit is a lightweight, flexible and novel open source poc verification framework

Comments

About the extracted embeddings.

Reproducing baseline1

omegaconf.errors.ConfigAttributeError: Missing key

speaker_loss.weight is not in the model.

Releases(v0.0.2)

v0.0.2(Jan 23, 2022)

Major update

v0.0.1(Jan 14, 2022)

Owner

(ICCV 2021) ProHMR - Probabilistic Modeling for Human Mesh Recovery

A Simplied Framework of GAN Inversion

EMNLP 2021 paper Models and Datasets for Cross-Lingual Summarisation.

Attack on Confidence Estimation algorithm from the paper "Disrupting Deep Uncertainty Estimation Without Harming Accuracy"

《LXMERT: Learning Cross-Modality Encoder Representations from Transformers》(EMNLP 2020)

Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

Codes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.

[ WSDM '22 ] On Sampling Collaborative Filtering Datasets

Unifying Global-Local Representations in Salient Object Detection with Transformer

Code for the KDD 2021 paper 'Filtration Curves for Graph Representation'

Implementation of self-attention mechanisms for general purpose. Focused on computer vision modules. Ongoing repository.

atmaCup #11 の Public 4th / Pricvate 5th Solution のリポジトリです。

MRI reconstruction (e.g., QSM) using deep learning methods

Python package for multiple object tracking research with focus on laboratory animals tracking.

基于PaddleOCR搭建的OCR server... 离线部署用

Generic Event Boundary Detection: A Benchmark for Event Segmentation

[ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models

"Segmenter: Transformer for Semantic Segmentation" reproduced via mmsegmentation

Code for SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics (ACL'2020).

Unofficial implementation of Proxy Anchor Loss for Deep Metric Learning