This is a really interesting article, I've stuttered while using Siri. > Rudzicz said he believes that voice-assistant technology is about “90 percent of the way there” to fully understanding people with non-fluent speech. The last 10 percent will come when the technology can create and memorize individual speech models for every user. I think an improvement in the technology's ability to understand language semantics would also be a significant jump for accommodating stutterers (easier said than done). Humans can determine if what they've heard so far makes sense, and how likely it is that the the speaker has finished what they were saying. We don't have to rely on pauses in sound to decide whether someone has finished a sentence.