Dsalign handling disfluencies

[JRMeyer]

>>> nmstoker
[September 13, 2019, 6:26pm]

[ slash tilman_kamp](
With the forced alignment tool, are there any particular approaches to
take with regard to disfluencies (esp fillers like um, ah, etc)

I'm interested in using it for a source that has sections of audio with
fairly frequent cases of them. I suspect it would be labour intensive to
identify them and adjust the transcripts (which don't reference them
currently, it's just regular text). I realise the best test it to try
it, but do you have any feeling for how resilient it is with that kind
of thing in general?

[This is an archived TTS discussion thread from discourse.mozilla.org/t/dsalign-handling-disfluencies]

[JRMeyer]

>>> Tilman_Kamp
[September 16, 2019, 9:16am]

I am currently aligning a data-set like this. The audio is
conversational while the original transcript ignores that disfluencies.
Some observations:

the algorithm is pretty resilient and just ignores them.
the typical places for disfluencies) could in extreme cases cause
the aligner to let the statement also eat up characters of the
previous or next utterance. In this case you already 'lost' two
utterances.
--align-similarity-algo has the most influence on the behavior.

'Between utterances' alignment behavior can be further fine-tuned
through parameters

[Archived Post]

[JRMeyer]

>>> nmstoker
[September 16, 2019, 12:04pm]

Many thanks
[ slash Tilman_Kamp](
that's very helpful to know and has convinced me to give it a go soon.
Thanks again for open sourcing a great project liked this one

[Archived Post]