TL;DR本文提出了LSD（潜在序列分解）框架，使用训练算法和解码算法，结合编码器和卷积网络进行语音识别，在Wall Street Journal的数据集上取得了优异的成果。
Abstract
We present the latent sequence decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output sequence. We present a training algorit