【24h】

Large Vocabulary SOUL Neural Network Language Models

机译:大词汇量SOUL神经网络语言模型

获取原文

摘要

This paper presents continuation of research on Structured OUt-put Layer Neural Network language models (SOUL NNLM) for automatic speech recognition. As SOUL NNLMs allow estimating probabilities for all in-vocabulary words and not only for those pertaining to a limited shortlist, we investigate its performance on a large-vocabulary task. Significant improvements both in perplexity and word error rate over conventional shortlist-based NNLMs are shown on a challenging Arabic GALE task characterized by a recognition vocabulary of about 300k entries. A new training scheme is proposed for SOUL NNLMs that is based on separate training of the out-of-shortlist part of the output layer. It enables using more data at each iteration of a neural network without any considerable slow-down in training and brings additional improvements in speech recognition performance.
机译:本文提出了用于自动语音识别的结构化输出层神经网络语言模型(SOUL NNLM)的研究的继续。由于SOUL NNLM不仅可以估计所有词汇中单词的概率,而且不仅可以估计那些与有限候选单词有关的单词的概率,因此我们还可以研究其在大型词汇任务中的表现。在一项具有挑战性的阿拉伯GALE任务(其特征在于约30万个条目的识别词汇表)中,显示了与传统的基于短名单的NNLM相比,困惑度和单词错误率都得到了显着改善。针对SOUL NNLM,提出了一种新的训练方案,该方案基于对输出层的入围名单之外部分的单独训练。它可以在神经网络的每次迭代中使用更多数据,而不会显着降低训练速度,并在语音识别性能方面带来了其他改进。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号