通过定制MWER损失准则改进端到端ASR中的专有名词识别
Improving Proper Noun Recognition in End-to-End ASR By Customization of the MWER Loss Criterion
摘要：
专有名词对端到端（E2E）自动语音识别（ASR）系统提出了挑战，因为特定名称在训练期间可能很少出现，并且可能具有与更常见单词的发音相似的发音。与传统的ASR模型不同，E2E系统缺乏可以用专有名词发音专门训练的显式发音模型和可以在大型纯文本语料库上训练的语言模型。过去的工作已经通过引入额外的训练数据或额外的模型来解决这个问题。在本文中，我们基于最小单词错误率（MWER）训练的最新进展，开发了两个新的损失标准，专门强调专有名词识别。与过去在这个问题上的工作不同，这种方法在训练过程中不需要新数据，在推理过程中也不需要外部模型。我们看到，在几个相关基准上，相对于2%到7%的改进。
英文摘要：
Proper nouns present a challenge for end-to-end (E2E) automatic speech recognition (ASR) systems in that a particular name may appear only rarely during training, and may have a pronunciation similar to that of a more common word. Unlike conventional ASR models, E2E systems lack an explicit pronounciation model that can be specifically trained with proper noun pronounciations and a language model that can be trained on a large text-only corpus. Past work has addressed this issue by incorporating additional training data or additional models. In this paper, we instead build on recent advances in minimum word error rate (MWER) training to develop two new loss criteria that specifically emphasize proper noun recognition. Unlike past work on this problem, this method requires no new data during training or external models during inference. We see improvements ranging from 2% to 7% relative on several relevant benchmarks.
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。
