This procedure has, until now, only been able to decode recognition results with dictated words differentiated from command words. There are some scenarios where recognition results do not have this characteristic, resulting in recognition failure.
This limitation is done away with here; the procedure now treats all result words properly. The DNS/Natlink behaviour described in issue number #242, and partially fixed in #268, is now properly fixed. The change also removes the need to use uppercase letters to successfully match dictation elements with the text-input ("text") and CMU Pocket Sphinx ("sphinx") engine back-ends.
This procedure has, until now, only been able to decode recognition results with dictated words differentiated from command words. There are some scenarios where recognition results do not have this characteristic, resulting in recognition failure.
This limitation is done away with here; the procedure now treats all result words properly. The DNS/Natlink behaviour described in issue number #242, and partially fixed in #268, is now properly fixed. The change also removes the need to use uppercase letters to successfully match dictation elements with the text-input ("text") and CMU Pocket Sphinx ("sphinx") engine back-ends.