We present a novel conversational-context aware end-to-end speech recognizer
based on a gated neural network that incorporates
conversational-context/word/speech embeddings. Unlike conventional speech
recognition models, our model learns longer conversational-context information
that spans across sentences and is consequently better at recognizing long
conversations. Specifically, we propose to use the text-based external word
and/or sentence embeddings (i.e., fastText, BERT) within an end-to-end
framework, yielding a significant improvement in word error rate with better
conversational-context representation. We evaluated the models on the
Switchboard conversational speech corpus and show that our model outperforms
standard end-to-end speech recognition models.

本文提出一种新颖的基于门控神经网络的语音识别模型，采用对话上下文 / 词 / 语音嵌入，结合外部词和 / 或句子嵌入来提高对话上下文表示，从而显著提高单词错误率，对 Switchboard 对话语音语料库的实验表明我们的模型优于标准的端到端语音识别模型。

对话上下文融合的端到端语音识别中的门控嵌入

Gated Embeddings in End-to-End Speech Recognition for  Conversational-Context Fusion

Achieving high accuracy with end-to-end speech recognizers requires careful
parameter initialization prior to training. Otherwise, the networks may fail to
find a good local optimum. This is particularly true for online networks, such
as unidirectional LSTMs. Currently, the best strategy to train such systems is
to bootstrap the training from a tied-triphone system. However, this is time
consuming, and more importantly, is impossible for languages without a
high-quality pronunciation lexicon. In this work, we propose an initialization
strategy that uses teacher-student learning to transfer knowledge from a large,
well-trained, offline end-to-end speech recognition model to an online
end-to-end model, eliminating the need for a lexicon or any other linguistic
resources. We also explore curriculum learning and label smoothing and show how
they can be combined with the proposed teacher-student learning for further
improvements. We evaluate our methods on a Microsoft Cortana personal assistant
task and show that the proposed method results in a 19 % relative improvement
in word error rate compared to a randomly-initialized baseline system.

提供了一种利用师生学习技术将离线的端到端语音识别模型的知识传递到在线端到端模型中的初始化策略，用以提高在线语音识别的准确性，并结合课程学习和标签平滑实现了更好的效果。在 Microsoft Cortana 的个人助手任务中，相比随机初始化基线系统，通过所提出的方法，可以使错误率相对下降了 19%。