Trans-dimensional random field language models (TRF LMs) where sentences are
modeled as a collection of random fields, have shown close performance with
LSTM LMs in speech recognition and are computationally more efficient in
inference. However, the training efficiency of neural TRF LMs is not
satisfactory, which limits the scalability of TRF LMs on large training corpus.
In this paper, several techniques on both model formulation and parameter
estimation are proposed to improve the training efficiency and the performance
of neural TRF LMs. First, TRFs are reformulated in the form of exponential
tilting of a reference distribution. Second, noise-contrastive estimation (NCE)
is introduced to jointly estimate the model parameters and normalization
constants. Third, we extend the neural TRF LMs by marrying the deep
convolutional neural network (CNN) and the bidirectional LSTM into the
potential function to extract the deep hierarchical features and
bidirectionally sequential features. Utilizing all the above techniques enables
the successful and efficient training of neural TRF LMs on a 40x larger
training set with only 1/3 training time and further reduces the WER with
relative reduction of 4.7% on top of a strong LSTM LM baseline.

本文提出了几种技术来提高神经随机场语言模型 (TRF LMs) 的训练效率和性能。这些技术包括参数估计和模型构建等，采用这些技术可以成功地、高效地训练神经 TRF LMs，并且在强 LSTM LM 基线的基础上将 WER 相对降低了 4.7% 左右。