I know it becomes harder to find the start and end of phonemes due to co-articulation. I want to know about other problems that co-articulation causes in speech recognition.
Modern data-driven approaches to speech recognition are ignorant about but robust to this one of many aspects of orthography that are not fully phonetic but occur relatively consistently in the training data.
For one, it is more an issue of mapping n:1 (different realisations of one set of characters), whereas challenges for speech recognition generally revolve around:
wreck a nice beachvs
meta language like
contact at priceline.comvs
He told me quote unquote I will kill youvs
He told me "I will kill you.", acronyms
shift vis-a-vis the training data:
out-of-domain and domain-specific words
variations in accents and dialects
a foreign language or mixed language
the fact that users don't really want a literal transcription:
I'ma, um, I'ma call you on, um, Saturdayvs
I'm going to call you on Saturday