REDAT：重标记领域对抗训练的端到端ASR的重音不变表示
REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling
摘要：
口音不匹配是端到端ASR的关键问题。本文旨在通过构建一个具有领域对抗训练（DAT）的口音鲁棒RNN-T系统来解决这个问题。我们揭示了DAT背后的魔力，并首次提供了DAT学习重音不变表示的理论保证。我们还证明了在DAT中执行梯度反转等价于最小化域输出分布之间的Jensen-Shannon散度。出于等价性证明的动机，我们引入了reDAT，这是一种基于DAT的新技术，它使用无监督聚类或软标签重新标记数据。在23 K小时的多口音数据上的实验表明，DAT在本地和非本地英语口音的口音特定基线上取得了有竞争力的结果，但在看不见的口音上相对WER减少了13%;我们的reDAT在美国和英国英语的非本地口音上比DAT进一步提高了3%和8%。
英文摘要：
Accents mismatching is a critical problem for end-to-end ASR. This paper aims to address this problem by building an accent-robust RNN-T system with domain adversarial training (DAT). We unveil the magic behind DAT and provide, for the first time, a theoretical guarantee that DAT learns accent-invariant representations. We also prove that performing the gradient reversal in DAT is equivalent to minimizing the Jensen-Shannon divergence between domain output distributions. Motivated by the proof of equivalence, we introduce reDAT, a novel technique based on DAT, which relabels data using either unsupervised clustering or soft labels. Experiments on 23K hours of multi-accent data show that DAT achieves competitive results over accent-specific baselines on both native and non-native English accents but up to 13% relative WER reduction on unseen accents; our reDAT yields further improvements over DAT by 3% and 8% relatively on non-native accents of American and British English.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
