子词正则化:端到端自动语音识别的可扩展性和泛化性分析
Subword Regularization: An Analysis of Scalability and Generalization for End-to-End Automatic Speech Recognition
摘要:
子字是端到端语音识别中应用最广泛的输出单元。它们通过直接对大多数频繁出现的单词进行建模,结合了两个世界中最好的一个,同时允许开放词汇语音识别,通过后退到较短的单元或字符来构建在训练过程中看不到的单词。然而,将文本映射到子词是模糊的,并且通常可能有多个分割变体。然而,许多系统只使用最可能的分割来训练。最近的研究表明,在训练过程中对子词分割进行采样可以作为神经机器翻译和语音识别模型的正则化器,从而提高性能。在这项工作中,我们进行了一个原则性的调查的规则化效果的子词分割采样方法的流端到端的语音识别任务。特别是,我们根据训练数据集的大小来评估子字正则化的贡献。我们的研究结果表明,子字正则化提供了(2-8%)相对字错误率降低的一致改进,即使在数据集大小高达20 k小时的大规模设置中。此外,我们分析了子字正则化对识别未见过的单词及其对波束多样性的影响。
英文摘要:
Subwords are the most widely used output units in end-to-end speech recognition. They combine the best of two worlds by modeling the majority of frequent words directly and at the same time allow open vocabulary speech recognition by backing off to shorter units or characters to construct words unseen during training. However, mapping text to subwords is ambiguous and often multiple segmentation variants are possible. Yet, many systems are trained using only the most likely segmentation. Recent research suggests that sampling subword segmentations during training acts as a regularizer for neural machine translation and speech recognition models, leading to performance improvements. In this work, we conduct a principled investigation on the regularizing effect of the subword segmentation sampling method for a streaming end-to-end speech recognition task. In particular, we evaluate the subword regularization contribution depending on the size of the training dataset. Our results suggest that subword regularization provides a consistent improvement of (2-8%) relative word-error-rate reduction, even in a large-scale setting with datasets up to a size of 20k hours. Further, we analyze the effect of subword regularization on recognition of unseen words and its implications on beam diversity.
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。