TL;DR本研究提出了一种基于深度神经网络的语音识别模型,它使用直连和双向 LSTM 来提高信息传递效率,并在 AMI DSR 任务上取得了显著的性能提升。
Abstract
In this paper, we extend the deep long short-term memory (DLSTM) recurrent
neural networks by introducing gated direct connections between memory cells in
adjacent layers. These direct links, called highway connections, enable
unimpeded information flow across different layers and thus