Speech database
From Phonlab
Revision as of 15:27, 26 May 2017 by Keithjohnson (talk | contribs)
The procedure outlined here uses utilities in the Berkeley Phonetic Machine, to produce time aligned TextGrids for recorded utterances in English.
1. create text transcripts of the words spoken in a sound file. Most plain text editors will be fine for this.
-- One potential complication is that plain text on windows may be saved "end of line" characters that are not compatible with <make_text_grids> - the perl utility that parses transcripts and passes them to <pyalign.py>. You can use the unix utility _d2u_ to change the line endings (this is a separate download into your instance of the BPM).