In this paper we show how we have achieved the state-of-the-art performance
on the industry-standard NIST 2000 Hub5 English evaluation set. We explore
densely connected LSTMs, inspired by the densely connected convolutional
networks recently introduced for image classification tasks. We also propose an
acoustic model adaptation scheme that simply averages the parameters of a seed
neural network acoustic model and its adapted version. This method was applied
with the CallHome training corpus and improved individual system performances
by on average 6.1% (relative) against the CallHome portion of the evaluation
set with no performance loss on the Switchboard portion. With RNN-LM rescoring
and lattice combination on the 5 systems trained across three different phone
sets, our 2017 speech recognition system has obtained 5.0% and 9.1% on
Switchboard and CallHome, respectively, both of which are the best word error
rates reported thus far. According to IBM in their latest work to compare human
and machine transcriptions, our reported Switchboard word error rate can be
considered to surpass the human parity (5.1%) of transcribing conversational
telephone speech.

论文展示了达到了 NIST 2000 Hub5 英语评估集的最先进表现，提出了一种基于密集连接 LSTMs 并激发于图像分类任务的密集连接卷积网络的方法，以及一个声学模型适应方案，并在 CallHome 训练语料库上应用了该方法，并在评估集的 CallHome 部分中平均提高了 6.1％（相对误差率），并且在 Switchboard 部分没有性能损失。