You are here:Home Practical exercises Build your own DNN voice Prepare the input labels Convert utterance structures to full context labels

Convert utterance structures to full context labels

We will 'flatten' the utterance structures onto a linear sequence of context-dependent phone labels.

  • Dump features

    First we use Festival to extract the information we want from the utterance structures

  • Full context labels

    Then we assemble the information into full context labels