Reuters published an article on Thursday that reveals some of the painstaking work that goes into making Siri capable of speaking additional languages, which remains one of its biggest strengths over rival virtual assistants.
The behind-the-scenes look appears amid claims that Apple has squandered its lead in the voice-assistant space, with Amazon, Google, and Microsoft all advancing the features of their respective assistants recently.
But for a smartphone market in which most sales are outside the U.S., Siri’s big advantage over the other assistants is underlined in the number of languages it can speak. Microsoft is said to have an editorial team of 29 people who work to customize Cortana for local markets, while Google and Amazon say they plan to add more languages soon. But it’s a game of catch-up: Apple already has 21 languages, localized for 36 countries. That compares favorably to Microsoft’s Cortana (eight), Google Assistant (four), and Amazon’s Alexa (two).
At Apple, the company starts working on a new language by bringing in humans to read passages in a range of accents and dialects, which are then transcribed by hand so the computer has an exact representation of the spoken text to learn from, said Alex Acero, head of the speech team at Apple. Apple also captures a range of sounds in a variety of voices. From there, a language model is built that tries to predict words sequences.