Voice Deepfake Detection Using the Self-Supervised Pre-Training Model HuBERT
Open Access
- 22 July 2023
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 13 (14) , 8488
Abstract
In recent years, voice deepfake technology has developed rapidly, but current detection methods have the problems of insufficient detection generalization and insufficient feature extraction for unknown attacks. This paper presents a forged speech detection method (HuRawNet2_modified) based on a self-supervised pre-trained model (HuBERT) to improve detection (and address the above problems). A combination of impulsive signal-dependent additive noise and additive white Gaussian noise was adopted for data boosting and augmentation, and the HuBERT model was fine-tuned on different language databases. On this basis, the size of the extracted feature maps was modified independently by the α-feature map scaling (α-FMS) method, with a modified end-to-end method using the RawNet2 model as the backbone structure. The results showed that the HuBERT model could extract features more comprehensively and accurately. The best evaluation indicators were an equal error rate (EER) of 2.89% and a minimum tandem detection cost function (min t-DCF) of 0.2182 on the database of the ASVspoof2021 LA challenge, which verified the effectiveness of the detection method proposed in this paper. Compared with the baseline systems in databases of the ASVspoof 2021 LA challenge and the FMFCC-A, the values of EER and min t-DCF decreased. The results also showed that the self-supervised pre-trained model with fine-tuning can extract acoustic features across languages. And the detection can be slightly improved when the languages of the pre-trained database, and the fine-tuned and tested database are the same.Keywords
Funding Information
- Double First-Class Innovation Research Project for People’s Public Security University of China (2023SYL07)
This publication has 25 references indexed in Scilit:
- End-to-End anti-spoofing with RawNet22021
- ASVspoof 2019: Spoofing Countermeasures for the Detection of Synthesized, Converted and Replayed SpeechIEEE Transactions on Biometrics, Behavior, and Identity Science, 2021
- An efficient real-valued sparse Bayesian learning for non-circular signal's DOA estimation in the presence of impulsive noiseDigital Signal Processing, 2020
- Improved RawNet with Feature Map Scaling for Text-Independent Speaker Verification Using Raw Waveforms2020
- ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification2020
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition2019
- wav2vec: Unsupervised Pre-Training for Speech Recognition2019
- I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification2018
- Constant Q cepstral coefficients: A spoofing countermeasure for automatic speaker verificationComputer Speech & Language, 2017
- A New Feature for Automatic Speaker Verification Anti-Spoofing: Constant Q Cepstral Coefficients2016