News for hackers. Stuff that matters.

A comment on Launch HN: AssemblyAI (YC S17) – API for customizable speech recognition. Parent comment

Re:Launch HN: AssemblyAI (YC S17) – API for customizable spe... by woodson on Saturday August 05, 2017 @03:37AM (#14934635)
You can create phonemic transcriptions as a back-off for unknown words (at least in WFST based setups), but with things like "sequel" this won't help much.
[ Parent | on HN ]
Re:Launch HN: AssemblyAI (YC S17) – API for customizable spe... by yorwba on Saturday August 05, 2017 @04:55AM (#14934854)
AssemblyAI is apparently using their own TensorFlow implementation, not weighted finite-state transducers like e.g. Kaldi.

Speaking about WFSTs, why wouldn't it work for "sequel"? I have only done the "Kaldi for Dummies" tutorial (i.e. digit recognition), but from what I understand, you could add an utterance "s iy k w eh l"/"SQL" and add phrases like "SQL query" to the corpus and this would make it more likely than "sequel query".

[ Parent | on HN ]