Conversational interfaces are a bit of a meme. Every couple of years a shiny new AI development emerges and people in tech go "This is it! The next computing paradigm is here! We'll only use natural language going forward!". But then nothing actually changes and we continue using computers the way w
In my own real world usage I estimate a comprehension rate of about 92% with voice agents.
For me it feels more like 9.2% most of the time, and that is just the voice-to-text part, not even the interpretation of the resulting text as a command.
Does feel like that, I agree, but if you spoke to someone who randomly completely misunderstood 8 out of every 100 words you said and had next to zero dead reckoning ability to figure out what that missing word was, I think you’d feel pretty frustrated.
I thought about it some more since I wrote my comment and I am genuinely unsure any voice recognition system I have ever used managed to transcribe a full sentence to text successfully without making at least one mistake.
On the other hand with a keyboard I am reasonably sure I get problems such as network filesystems being unable to reach the server or broken hard drives more often than having to worry about mistyping a command I commonly use. Granted, part of that is thanks to tab completion but that is part of the issue with voice input, no easy way to correct what it got wrong.
In English? Do you have an accent? Dragon is one of the better ones and it seems with many accents it does remarkably well. Google seems to have one of the worst I’ve come across.
Both in English and my native German. I probably do have an accent in English but that is difficult to judge myself. Certainly nothing that prevents other people from understanding me though.
For me it feels more like 9.2% most of the time, and that is just the voice-to-text part, not even the interpretation of the resulting text as a command.
Does feel like that, I agree, but if you spoke to someone who randomly completely misunderstood 8 out of every 100 words you said and had next to zero dead reckoning ability to figure out what that missing word was, I think you’d feel pretty frustrated.
I thought about it some more since I wrote my comment and I am genuinely unsure any voice recognition system I have ever used managed to transcribe a full sentence to text successfully without making at least one mistake.
On the other hand with a keyboard I am reasonably sure I get problems such as network filesystems being unable to reach the server or broken hard drives more often than having to worry about mistyping a command I commonly use. Granted, part of that is thanks to tab completion but that is part of the issue with voice input, no easy way to correct what it got wrong.
In English? Do you have an accent? Dragon is one of the better ones and it seems with many accents it does remarkably well. Google seems to have one of the worst I’ve come across.
Both in English and my native German. I probably do have an accent in English but that is difficult to judge myself. Certainly nothing that prevents other people from understanding me though.