Maximum-Entropy Adversarial Audio Augmentation for Keyword Spotting
ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2024)
摘要
Data augmentation is a key tool for improving the performance of deep
networks, particularly when there is limited labeled data. In some fields, such
as computer vision, augmentation methods have been extensively studied;
however, for speech and audio data, there are relatively fewer methods
developed. Using adversarial learning as a starting point, we develop a simple
and effective augmentation strategy based on taking the gradient of the entropy
of the outputs with respect to the inputs and then creating new data points by
moving in the direction of the gradient to maximize the entropy. We validate
its efficacy on several keyword spotting tasks as well as standard audio
benchmarks. Our method is straightforward to implement, offering greater
computational efficiency than more complex adversarial schemes like GANs.
Despite its simplicity, it proves robust and effective, especially when
combined with the established SpecAugment technique, leading to enhanced
performance.
更多查看译文
关键词
data augmentation,adversarial learning,keyword spotting
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要