Code for csig audio deepfake detection

Related tags

AudioCSIG_audio
Overview

FMFCC Audio Deepfake Detection Solution

This repo provides an solution for the 多媒体伪造取证大赛. Our solution achieve the 1st in the Audio Deepfake Detection track . The ranking can be seen here

Authors

Institution: Shenzhen Key Laboratory of Media Information Content Security(MICS)

Team name: Forensics_SZU

Username:

Pipeline

EfficientNet-B2 + mel features (不同mel参数的训练两个模型ensemble)

Requirements:

  • 激活已经配置好的环境[建议使用这个]
conda activate audio
  • 或者执行这个重新配置
pip install -r requirements.txt
  • 可能存在部分包漏了安装,可以通过pip install 方式继续安装完整

Submission

  • cd到代码位置:/home/audio5/py_project/CSIG_audio
cd /home/audio5/py_project/CSIG_audio
  • 接着,修改inference.py 文件的第98行中的root_path路劲为自己语音测试集的路劲

1. 预测第一个模型

  • 然后执行
python inference.py
  • 运行结束后,可以在 "./output/results/efficientnet-b2_96_k2e6_hop48_t' 看到results.json文件

2. 预测第二个模型

  • 2.1 修改json_root的路劲:把inference.py的105行的代码注释掉, 然后解除106行的注释,更新了第二个模型预测结果保存的路劲,修改后的代码如下
105        # json_root = f'./output/results/{model_name}_96_k2e6_hop48_t'
106        json_root = f'./output/results/{model_name}_96_k2e9_t'
  • 2.2 修改model_path的路劲(即改变模型权值):把inference.py的114行的代码注释掉, 然后解除115行的注释,更新了模型权值的路劲,修改后的代码如下
114        # model_path = './output/weights/efficientnet-b2_96_hop48_k2/audio6_acc0.9832.pth'
115        model_path = './output/weights/efficientnet-b2_96_k2/audio9_acc0.9752.pth'
  • 2.3 修改mel feature的配置参数:把dataset/preprocess/vggish_params.py中的 35行代码"EXAMPLE_HOP_SECONDS = 0.48" 改为"EXAMPLE_HOP_SECONDS = 0.96" 特别要注意EXAMPLE_HOP_SECONDS这个参数,验证结束后,需要重新修改为0.48, 方便最终决赛运行
  • 修改上述三点后,然后执行, 另外前面的两个修改也需要恢复。
python inference.py
  • 运行结束后,可以在 "./output/results/efficientnet-b2_96_k2e9_t' 看到results.json文件

Ensemble

  • 集成刚刚生成的两个json文件:把inference.py 第88行的"json_ensemble = False"改为"json_ensemble = True"
  • 修改后执行:
python inference.py
  • 运行结束后,可以在 "./output/results/ensemble_01_t' 看到results.json文件,该文件就是我们最终提交的结果json文件

注意:验证结束后,需要恢复上述修改到原始状态,方便最终的决赛

Owner
BokingChen
BokingChen
commonfate 📦commonfate 📦 - Common Fate Model and Transform.

Common Fate Transform and Model for Python This package is a python implementation of the Common Fate Transform and Model to be used for audio source

Fabian-Robert Stöter 18 Jan 08, 2022
This library provides common speech features for ASR including MFCCs and filterbank energies.

python_speech_features This library provides common speech features for ASR including MFCCs and filterbank energies. If you are not sure what MFCCs ar

James Lyons 2.2k Jan 04, 2023
The official repository for Audio ALBERT

AALBERT Here is also the official repository of AALBERT, which is Pytorch lightning reimplementation of the paper, Audio ALBERT: A Lite Bert for Self-

pohan 55 Dec 11, 2022
An audio guide for destroying oracles in Destiny's Vault of Glass raid

prophet An audio guide for destroying oracles in Destiny's Vault of Glass raid. This project allows you to make any encounter with oracles without hav

24 Sep 15, 2022
Delta TTA(Text To Audio) SoftWare

Text-To-Audio-Windows Delta TTA(Text To Audio) SoftWare Info You Can Use It For Convert Your Text To Audio File You Just Write Your Text And Your End

Delta Inc. 2 Dec 14, 2021
Codes for "Efficient Long-Range Attention Network for Image Super-resolution"

ELAN Codes for "Efficient Long-Range Attention Network for Image Super-resolution", arxiv link. Dependencies & Installation Please refer to the follow

xindong zhang 124 Dec 22, 2022
TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music

TONet Introduction The official implementation of "TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music", in ICASSP 2022 We

Knut(Ke) Chen 29 Dec 01, 2022
Reading list for research topics in sound event detection

Sound event detection aims at processing the continuous acoustic signal and converting it into symbolic descriptions of the corresponding sound events present at the auditory scene.

Soham 64 Jan 05, 2023
Conferencing Speech Challenge

ConferencingSpeech 2021 challenge This repository contains the datasets list and scripts required for the ConferencingSpeech challenge. For more detai

73 Nov 29, 2022
Voice package for Pycord adding extra features.

VoiceIO Voice package for Pycord adding extra features. Example Down bellow is an example of what you can currently do. import voiceio process = voic

pycord 1 Dec 24, 2021
An audio-solving python funcaptcha solving module

funcapsolver funcapsolver is a funcaptcha audio-solving module, which allows captchas to be interacted with and solved with the use of google's speech

Acier 8 Nov 21, 2022
Mentos Music Bot With Python

Mentos Music Bot For Any Query Join Our Support Group 👥 Special Thanks - @OfficialYukki Hey Welcome To Here 💫 💫 You Can Make Your Own Music Bot Fo

Cyber Toxic 13 Oct 21, 2022
Generating a structured library of .wav samples with Python.

sample-library Scripts for generating a structured sample library with Python Requires Docker about Samples are written to wave files in lib/. Differe

Ben Mangold 1 Nov 11, 2021
SolidMusic rewrite version, need help

Telegram Streamer Bot This is rewrite version of solidmusic, but it can't be deployed now, help me to make this bot running fast and good. If anyone w

Shohih Abdul 63 Jan 06, 2022
Multi-Track Music Generation with the Transfomer and the Johann Sebastian Bach Chorales dataset

MMM: Exploring Conditional Multi-Track Music Generation with the Transformer and the Johann Sebastian Bach Chorales Dataset. Implementation of the pap

102 Dec 08, 2022
Music Streaming Platform based on full implementation of DBSM

Symphony Music Streaming Platform based on full implementation of DBSM List of Commands Insert User (INSERT) Function to implement input in USER Get a

Parth Maradia 1 Nov 12, 2021
a library for audio and music analysis

aubio aubio is a library to label music and sounds. It listens to audio signals and attempts to detect events. For instance, when a drum is hit, at wh

aubio 2.9k Dec 30, 2022
Stevan KZ 1 Oct 27, 2021
Nayeli: cool telegram groups vc music project

Nayeli-music Nayeli 🥀 is cool telegram 🍎 groups vc music project 🎋 . Nayeli-music Nayeli Deployment 🎋 📲 Esy deploy 🐾️ Source Owner ♥️ ❄️ He is s

Kasun bandara 2 Dec 20, 2021
Audio Retrieval with Natural Language Queries: A Benchmark Study

Audio Retrieval with Natural Language Queries: A Benchmark Study Paper | Project page | Text-to-audio search demo This repository is the implementatio

21 Oct 31, 2022