Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition
Conference of the International Speech Communication Association (INTERSPEECH)(2022)
摘要
Learning continually from data is a task executed effortlessly by humans but remains to be of significant challenge for machines. Moreover, when encountering unknown test scenarios machines fail to generalize. We propose a mathematically motivated dynamically expanding end-to-end model of independent sequence-to-sequence components trained on different data sets that avoid catastrophically forgetting knowledge acquired from previously seen data while seamlessly integrating knowledge from new data. During inference, the likelihoods of the unknown test scenario are computed using internal model activation distributions. The inference made by each independent component is weighted by the normalized likelihood values to obtain the final decision.
更多查看译文
关键词
speech recognition, continual learning, multi stream speech recognition
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