Population Based Training for Data Augmentation and Regularization in Speech Recognition

arxiv(2020)

引用 0|浏览17
暂无评分
摘要
Varying data augmentation policies and regularization over the course of optimization has led to performance improvements over using fixed values. We show that population based training is a useful tool to continuously search those hyperparameters, within a fixed budget. This greatly simplifies the experimental burden and computational cost of finding such optimal schedules. We experiment in speech recognition by optimizing SpecAugment this way, as well as dropout. It compares favorably to a baseline that does not change those hyperparameters over the course of training, with an 8% relative WER improvement. We obtain 5.18% word error rate on LibriSpeech's test-other.
更多
查看译文
关键词
data augmentation,speech recognition,regularization,population based training
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