论文标题
在高错误识别方案中语言模型的文本增强
Text Augmentation for Language Models in High Error Recognition Scenario
论文作者
论文摘要
我们研究了数据扩展对语言模型培训语音识别的影响。我们将基于全球错误统计数据的增强与基于ASR错误的每个单词统计数据进行比较，并观察到最好仅关注全球替代，删除和插入率。这个简单的方案也比标签平滑及其采样变体始终如一。此外，我们研究了在增强数据上估计的困惑性的行为，但得出的结论是，它不能更好地预测最终错误率。我们最佳的增强计划将Chime-6挑战的绝对重新赛车从第二频繁的回归从1.1％提高到1.9％。
We examine the effect of data augmentation for training of language models for speech recognition. We compare augmentation based on global error statistics with one based on per-word unigram statistics of ASR errors and observe that it is better to only pay attention the global substitution, deletion and insertion rates. This simple scheme also performs consistently better than label smoothing and its sampled variants. Additionally, we investigate into the behavior of perplexity estimated on augmented data, but conclude that it gives no better prediction of the final error rate. Our best augmentation scheme increases the absolute WER improvement from second-pass rescoring from 1.1 % to 1.9 % absolute on the CHiMe-6 challenge.
