ConvNeXt Based Neural Network for Audio Anti-Spoofing
Autor: | Ma, Qiaowei, Zhong, Jinghui, Yang, Yitao, Liu, Weiheng, Gao, Ying, Ng, Wing W. Y. |
---|---|
Rok vydání: | 2022 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | With the rapid development of speech conversion and speech synthesis algorithms, automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. In recent years, researchers had proposed a number of anti-spoofing methods based on hand-crafted features. However, using hand-crafted features rather than raw waveform will lose implicit information for anti-spoofing. Inspired by the promising performance of ConvNeXt in image classification tasks, we revise the ConvNeXt network architecture and propose a lightweight end-to-end anti-spoofing model. By integrating with the channel attention block and using the focal loss function, the proposed model can focus on the most informative sub-bands of speech representations and the difficult samples that are hard to classify. Experiments show that our proposed system could achieve an equal error rate of 0.64% and min-tDCF of 0.0187 for the ASVSpoof 2019 LA evaluation dataset, which outperforms the state-of-the-art systems. Comment: 6 pages |
Databáze: | arXiv |
Externí odkaz: |