Beyond getting the phones right, we also need to consider other aspects of speech such as intonation and pausing.

Each word in the normalised text needs a pronunciation. Most words will be found in the dictionary, but for the remainder we must predict pronunciation from spelling.

We need to normalise the input text so that it contains a sequence of pronounceable words.

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.