kaldi学习之汇总

一、特有名词

acoustic scale:　通常设置为0.1，意味着声学模型的log概率得到的权重远低于语言模型。在Score的脚本中，经常会看到一系列要搜索的语言模型权重（例如7到15的范围）。 这些可以解释为声acoustic scale的倒数; 这是两者对维特比解码很重要的比例

alignment：表示一句话通过维特比(最佳路径)对齐的HMM状态序列表示，与transtions-id同义。show-alignment显示

likelihood:使用标准的交叉熵训练的神经网络系统，我们通过将对数概率除以上下文相关状态的先验来获得“伪似然性”。

posterior:后验概率，Alignments and lattices can be converted to posteriors over transition-ids (see lattice-to-post.cc), or over lattice arcs (see ali-to-post.cc and lattice-arc-post.cc). Posteriors over transition-ids can be converted to posteriors over pdf-ids or over phones; see the tools ali-to-post.cc, post-to-pdf-post.cc and post-to-phone-post.cc

二、关于lattice的工具

 latgen-faster-mapped：  生成lattice 

lattice-scale：Apply scaling to lattice weights

lattice-add-penalty： Add word insertion penalty to the lattice

lattice-best-path： Generate 1-best path through lattices; output as transcriptions and alignments

lattice-align-words： Convert lattices so that the arcs in the CompactLattice format correspond with words

lattice-align-phones：Convert lattices so that the arcs in the CompactLattice format correspond with phones