Transcript Alignment

The align module compares speech-to-text output with a normalized transcript file to produce a transcript that contains a timestamp for each word.

The ctm module reads the speech-to-text output file.

w is the time-marked word series.


The align module takes each word record and aligns it against the preloaded, normalized transcript and outputs time-coded transcript words.

w is the output time-marked word series.


The wout module prepares the output phrase labels and time positions for storage and result reporting.

The schema that implements this feature is:

[MyTranscriptAlign]
w ← ctm (READ, input)
w2 ← align(SCORE, input)
output ← wout(_, w2)

_FT_HTML5_bannerTitle.htm