The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio

Authors:
Yuankun Xie, Yi Lu, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Jianhua Tao, Xin Qi, Xiaopeng Wang, Yukun Liu, Haonan Cheng, Long Ye, Yi Sun

 

Abstract:
The paper focuses on detecting audio deepfakes generated by Audio Language Models (ALMs), which produce highly realistic and diverse audio. The authors first create a large-scale dataset called Codecfake, containing over 1 million audio samples (real and fake in English and Chinese), specifically targeting ALM-based audio generated through neural codec-to-waveform processes. They then propose a new training strategy called CSAM (a modified Sharpness-Aware Minimization) to improve model generalization and avoid domain bias. Using this dataset and training approach, they show that detectors can better identify ALM-generated deepfakes and achieve very low error rates, significantly outperforming existing methods.

 

Data Creation Method:
Seven neural codec models were trained on LibriTTS, then used to re-encode and decode real audio from VCTK and AISHELL3 to create codec-based fake audio. The neural codec models were trained on LibriTTS, a 585-hour, 24 kHz multi-speaker English corpus, using default or ALM-adopted parameter settings until convergence.

 

Number of Speakers:

  • 328 speakers inferred from source datasets

Total Size:

  • 1,058,216 audio samples

Number of Real Samples:

  • 132,277 real samples total: 44,242 from VCTK and 88,035 from AISHELL3

Number of Fake Samples:

  • 925,939 fake samples generated by seven codec methods

Description of the Dataset:

  • Codecfake is an open-source, large-scale collection comprising over 1 million audio samples in both English and Chinese, focusing on ALM-based audio detection.

 

Extra Details:
F07 is held out as an unseen fake method for generalization testing. F07 is DAC and is excluded from training/development to test unseen-method generalization. The dataset also includes varied test conditions for codec methods, parameter changes, and ALM-based audio.

 

Data Type:

  • Audio samples
  • Speech and sound
  • Codec-based reconstructed waveform audio

Average Length:

  • Not specified

Keywords:

  • Audio deepfake dataset, audio deepfake detection, audio language model, neural codec

When Published:

  • 2025

 

Annotation Process:
No manual annotation process is described. The real/fake labels come from dataset construction: original source audio is real, and codec-generated audio is fake.

 

Usage Scenarios:
Training and evaluating audio deepfake detection models, especially for ALM-based and codec-based deepfake audio; testing generalization to unseen codec methods, varied codec parameters, and in-the-wild ALM-based audio.

 

Data Accessibility:
The dataset and code are available online through the Zenodo and GitHub links printed in the paper.

 

Miscellaneous Information:
Limitations and future work include adding more diverse audio types, more acoustic conditions, stronger generalized ADD methods, and source-tracing methods.

 

Credits:
Datasets Used:

  • For Codecfake creation: LibriTTS, VCTK, and AISHELL3
  • For ALM A3 testing: AudioCaps
  • For experimental comparison/co-training: ASVspoof2019LA / 19LA

Speech Synthesis Models Referenced:

  • Codec models used for Codecfake: SoundStream, SpeechTokenizer, FunCodec, EnCodec, AudioDec, AcademicCodec, DAC
  • ALM-based generation models referenced/tested include VALL-E, VALL-E X, AudioGen

Dataset Link


Main Paper Link


Last Accessed: 06/16/2026

NSF Award #2346473