Decision tree state tying based on penalized Bayesian information criterion
Decision tree state tying based on penalized Bayesian information criterion
复制标题
DOI：
10.1109/icassp.1999.758133
复制
发表时间：
1999-03
期刊：
影响因子：
--
通讯作者：
W. Chou;W. Reichl
中科院分区：
文献类型：
--
作者：
W. Chou;W. Reichl
本文提出了一种基于惩罚贝叶斯信息准则的决策树状态捆绑方法。pBIC应用于两个重要的应用。首先，它被用来作为一个决策树生长的标准，而不是传统的方法，使用启发式常数阈值。研究发现，原始BIC惩罚太低，不会导致一个紧凑的决策树状态捆绑模型。基于Wolfe对渐近零分布的修正，推导出基于pBIC的决策树状态捆绑应使用两倍BIC惩罚。其次，研究了pBIC作为决策树状态捆绑声学建模的模型压缩准则。大词汇量（华尔街日报）语音识别任务的实验结果表明，一个紧凑的决策树可以实现几乎没有损失的语音识别性能。
In this paper, an approach of the penalized Bayesian information criterion (pBIC) for decision tree state tying is described. The pBIC is applied to two important applications. First, it is used as a decision tree growing criterion in place of the conventional approach of using a heuristic constant threshold. It is found that original BIC penalty is too low and will not lead to a compact decision tree state tying model. Based on Wolfe's modification to the asymptotic null distribution, it is derived that two times BIC penalty should be used for decision tree state tying based on pBIC. Secondly, pBIC is studied as a model compression criterion for decision tree state tying based acoustic modeling. Experimental results on a large vocabulary (Wall Street Journal) speech recognition task indicate that a compact decision tree could be achieved with almost no loss of the speech recognition performance.