We can just use raw counts to estimate probabilities directly.

The frequency of occurrence of each N-gram in a training corpus is used to estimate its probability.

Important material on efficiently computing the combined likelihood of the acoustic model multiplied by the probability of the language model.

In connected speech, three types of error are possible: substitutions, insertions, or deletions of words. It is usual to combine them into a single measure: Word Error Rate.

Embedded training means that the data are transcribed, but that we don’t know the time alignment at the model or state levels.

Simply mentions the lexicon and language model and refers the reader to other chapters.