Text injection for automatic speech recognition (ASR), wherein unpaired
text-only data is used to supplement paired audio-text data, has shown
promising improvements for word error rate. This study examines the use of text
injection for auxiliary tasks, which are the non-ASR tasks often performed by
an E2E model. In this work, we use joint end-to-end and internal language model
training (JEIT) as our text injection algorithm to train an ASR model which
performs two auxiliary tasks. The first is capitalization, which is a
de-normalization task. The second is turn-taking prediction, which attempts to
identify whether a user has completed their conversation turn in a digital
assistant interaction. We show results demonstrating that our text injection
method boosts capitalization performance for long-tail data, and improves
turn-taking detection recall.

本研究通过使用文本注入算法来训练自动语音识别模型，以解决长尾数据的大写问题，并改善对话机器人中的交互转移预测。

语音模型中的大写和交替预测注入方法

Text Injection for Capitalization and Turn-Taking Prediction in Speech  Models

For those languages which use it, capitalization is an important signal for
the fundamental NLP tasks of Named Entity Recognition (NER) and Part of Speech
(POS) tagging. In fact, it is such a strong signal that model performance on
these tasks drops sharply in common lowercased scenarios, such as noisy web
text or machine translation outputs. In this work, we perform a systematic
analysis of solutions to this problem, modifying only the casing of the train
or test data using lowercasing and truecasing methods. While prior work and
first impressions might suggest training a caseless model, or using a truecaser
at test time, we show that the most effective strategy is a concatenation of
cased and lowercased training data, producing a single model with high
performance on both cased and uncased text. As shown in our experiments, this
result holds across tasks and input representations. Finally, we show that our
proposed solution gives an 8% F1 improvement in mention detection on noisy
out-of-domain Twitter data.

本研究通过修改大小写来解决 NLP 任务中大写信号的问题，将大小写训练数据串联起来可以使模型在大小写文本中都拥有良好的性能，同时对嘈杂的 Twitter 数据进行测试，结果表明我们的解决方案提高了 8％的 F1 检测率。