Probabilistic classification of HMM states for large vocabulary continuous speech recognition
Probabilistic classification of HMM states for large vocabulary continuous speech recognition
复制标题
用于大词汇量连续语音识别的 HMM 状态概率分类
DOI：
--
复制
发表时间：
1999
期刊：
影响因子：
--
通讯作者：
F. Jelinek
中科院分区：
文献类型：
--
作者：
Xiaoqiang Luo;F. Jelinek
在现有的大词汇量连续语音识别（LVCSR）系统中，HMM状态绑定通常用于在模型分辨率和鲁棒性之间取得良好的平衡。在这种范例中，绑定的HMM状态共享一组参数，并且是不可区分的。为了捕捉绑定HMM状态之间的细微差异，本文提出了一种用于LVCSR的HMM状态概率分类（PCHMM）。特别地，从HMM状态到类的分布被引入。示出了状态到类分布可以与EM内的常规HMM参数一起估计（Dempster等人，1977）框架。与HMM状态捆绑相比，HMM状态的概率分类更有效地利用了模型参数。它还使声学模型对训练数据和测试数据之间可能的失配或变化更加鲁棒。这种方法的可行性通过交换台上的字错误率（WER）的显著降低来验证（戈弗雷等人，1992年）的任务。
In state-of-art large vocabulary continuous speech recognition (LVCSR) systems, HMM state-tying is often used to achieve good balance between the model resolution and robustness. In this paradigm, tied HMM states share a single set of parameters and are nondistinguishable. To capture the fine differences among tied HMM states, a probabilistic classification of HMM states (PCHMM) is proposed in this paper for LVCSR. In particular, a distribution from a HMM state to classes is introduced. It is shown that the state-to-class distribution can be estimated together with conventional HMM parameters within the EM (Dempster et al., 1977) framework. Compared with HMM state-tying, probabilistic classification of HMM states makes more efficient use of model parameters. It also makes the acoustic model more robust against the possible mismatch or variation between training and test data. The viability of this approach is verified by the significant reduction of word error rate (WER) on the Switchboard (Godfrey et al., 1992) task.