自动化学报2012，Vol.38Issue(9)：1449-1458,10.DOI:10.3724/SP.J.1004.2012.01449
区分性模型组合中基于决策树的声学上下文建模方法
Discriminative Model Combination Using Decision Tree Based Phonetic Context Modeling
摘要
Abstract
One limitation of context dependent discriminative model combination is that a large number of parameters will be introduced, which is liable to overtraining with limited training data. We propose context modeling using phonetic decision trees in lattice based discriminative model combination. Question in tree node is chosen to optimize the minimum phone error criterion. First order approximation of the objective function increment is used for fast question selection. Results on speech recognition show that the method is capable of improving the robustness to overtraining and obtains error reduction with many fewer parameters. It is also shown that the model combination using tree based context modeling is superior to feature combination approach.关键词
区分性模型组合/上下文建模/声学决策树/最小音子错误/语音识别Key words
Discriminative mcfeel combination, context, decision tree, minimum phone error, speech recognition引用本文复制引用
黄浩,李兵虎,吾守尔·斯拉木..区分性模型组合中基于决策树的声学上下文建模方法[J].自动化学报,2012,38(9):1449-1458,10.基金项目
国家自然科学基金(60965002,60865001,61163026),新疆高校科研计划培育基金(XJEDU2008S15),新疆大学博士科研启动基金(BS090143)资助 （60965002,60865001,61163026）
