English

An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audio

Sound 2022-08-23 v1 Artificial Intelligence Audio and Speech Processing

Abstract

Many effective attempts have been made for fake audio detection. However, they can only provide detection results but no countermeasures to curb this harm. For many related practical applications, what model or algorithm generated the fake audio also is needed. Therefore, We propose a new problem for detecting vocoder fingerprints of fake audio. Experiments are conducted on the datasets synthesized by eight state-of-the-art vocoders. We have preliminarily explored the features and model architectures. The t-SNE visualization shows that different vocoders generate distinct vocoder fingerprints.

Keywords

Cite

@article{arxiv.2208.09646,
  title  = {An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audio},
  author = {Xinrui Yan and Jiangyan Yi and Jianhua Tao and Chenglong Wang and Haoxin Ma and Tao Wang and Shiming Wang and Ruibo Fu},
  journal= {arXiv preprint arXiv:2208.09646},
  year   = {2022}
}

Comments

Accepted by ACM Multimedia 2022 Workshop: First International Workshop on Deepfake Detection for Audio Multimedia