Hey ChatGPT — you talking to me?
If Siri and Alexa tend to misunderstand a lot of your requests, it could be that accent.
A new survey suggests the distinct intonations of folks from New York City, New Jersey and Long Island are amongst the hardest for artificial intelligence technology to decipher.
To absolutely no one’s surprise, Southern drawls top the list as the hardest accents for AI voice-recognition programs to understand, according to language resource site Guide2Fluency.
“Words like ‘y’all’ and ‘fixin’ to’ can be particularly perplexing for AI, leading to frequent misinterpretations,” the site said.
The New York City accent — perfect for buying some “gabagool” in Brooklyn, but not so great when AI is searching for capicola — followed in second, while New Jersey placed third.
The Texan accent ranked fourth hardest, the survey of 3,000 shows.
Shockingly, Bostonians came in at No. 5, not first.
“Accents from major urban centers” like New York City, New Jersey and Boston “often feature distinctive pronunciation and local slang that can trip up AI,” the site explains. “For instance, New Yorkers’ tendency to drop the ‘r’ sound (‘cah’ for ‘car’) or Bostonians’ famous ‘pahk the cah in Hahvahd Yahd’ can confuse voice recognition systems.”
Lawn Guylanders came in at No. 7. “The Long Island accent, with its nasal tone and elongated vowels, often leaves AI guessing,” the site explains.
Rounding out the Top 10 were the Appalachian accent (“That feller come a-runnin’ towards ma winder, askin’ for taters”); those from California’s San Fernando Valley (Think Jeff Spicoli’s “All I need are some tasty waves, a cool buzz, and I’m fine”); Miami, an accent influenced by immigrated Cubans; and folks who hail from N’Awlins.
Upstaters are not spared. The Hudson Valley accent — which is also known as “Albany English,” and features traces of Dutch combined with New York City’s short vowels — was identified as the 22nd hardest for AI to comprehend.
Ultimately, the site contends, “these misunderstandings have real-world implications,” with users who speak with these accents perceiving AI as “less reliable for everyday tasks, leading to frustration and a lack of trust in the technology.”