翻了23年前的语音检测相关论文,进行简单记录(比较好的标杆论文,而且都是熟悉的深度学习方法,而且也有代码)
23-04-05 update
- END-TO-END ANTI-SPOOFING WITH RAWNET2
- A Comparative Study on Recent Neural Spoofing Countermeasures for
Synthetic Speech Detection (LCNN) - SpecRNet: Towards Faster and More Accessible
Audio DeepFake Detection - 区域伪造检测:TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection:https://arxiv.org/abs/2306.15212
asvspoof-challenge:
https://github.com/asvspoof-challenge/2021 其中LA赛道是算法伪造检测赛道
https://github.com/asvspoof-challenge/2021/tree/main/LA/Baseline-LFCC-LCNN
LCNN代码
https://github.com/Jungjee/RawNet/tree/master/python
rawnet3
以上其他,可以自己谷歌搜相关论文和代码