Apple's Machine Learning Has Cut Siri's Error Rate by a Factor of Two

Steven Levy has published an in-depth article about Apple's artificial intelligence and machine learning efforts, after meeting with senior executives Craig Federighi, Eddy Cue, Phil Schiller, and two Siri scientists at the company's headquarters.

backchannel-apple-machine-learning
Apple provided Levy with a closer look at how machine learning is deeply integrated into Apple software and services, led by Siri, which the article reveals has been powered by a neural-net based system since 2014. Apple said the backend change greatly improved the personal assistant's accuracy.

"This was one of those things where the jump was so significant that you do the test again to make sure that somebody didn’t drop a decimal place," says Eddy Cue, Apple’s senior vice president of internet software and services.

Alex Acero, who leads the Siri speech team at Apple, said Siri's error rate has been lowered by more than a factor of two in many cases.

“The error rate has been cut by a factor of two in all the languages, more than a factor of two in many cases,” says Acero. “That’s mostly due to deep learning and the way we have optimized it — not just the algorithm itself but in the context of the whole end-to-end product.”

Acero told Levy he was able to work directly with Apple's silicon design team and the engineers who write the firmware for iOS devices to maximize performance of the neural network, and Federighi added that Apple building both hardware and software gives it an "incredible advantage" in the space.

"It's not just the silicon," adds Federighi. "It's how many microphones we put on the device, where we place the microphones. How we tune the hardware and those mics and the software stack that does the audio processing. It's all of those pieces in concert. It's an incredible advantage versus those who have to build some software and then just see what happens."

Apple's machine learning efforts extend far beyond Siri, as evidenced by several examples shared by Levy:

You see it when the phone identifies a caller who isn’t in your contact list (but did email you recently). Or when you swipe on your screen to get a shortlist of the apps that you are most likely to open next. Or when you get a reminder of an appointment that you never got around to putting into your calendar. Or when a map location pops up for the hotel you’ve reserved, before you type it in. Or when the phone points you to where you parked your car, even though you never asked it to. These are all techniques either made possible or greatly enhanced by Apple’s adoption of deep learning and neural nets.

Another product born out of machine learning is the Apple Pencil, which can detect the difference between a swipe, a touch, and a pencil input:

In order for Apple to include its version of a high-tech stylus, it had to deal with the fact that when people wrote on the device, the bottom of their hand would invariably brush the touch screen, causing all sorts of digital havoc. Using a machine learning model for “palm rejection” enabled the screen sensor to detect the difference between a swipe, a touch, and a pencil input with a very high degree of accuracy. “If this doesn’t work rock solid, this is not a good piece of paper for me to write on anymore — and Pencil is not a good product,” says Federighi. If you love your Pencil, thank machine learning.

On the iPhone, machine learning is enabled by a localized dynamic cache or "knowledge base" that Apple says is around 200MB in size, depending on how much personal information is stored.

This includes information about app usage, interactions with other people, neural net processing, a speech modeler, and "natural language event modeling." It also has data used for the neural nets that power object recognition, face recognition, and scene classification.

"It's a compact, but quite thorough knowledge base, with hundreds of thousands of locations and entities. We localize it because we know where you are," says Federighi. This knowledge base is tapped by all of Apple's apps, including the Spotlight search app, Maps, and Safari. It helps on auto-correct. "And it's working continuously in the background," he says.

Apple, for example, uses its neural network to capture the words iPhone users type using the standard QuickType keyboard.

Other information Apple stores on devices includes probably the most personal data that Apple captures: the words people type using the standard iPhone QuickType keyboard. By using a neural network-trained system that watches while you type, Apple can detect key events and items like flight information, contacts, and appointments — but information itself stays on your phone.

Apple insists that much of the machine learning occurs entirely local to the device, without personal information being sent back to its servers.

"Some people perceive that we can't do these things with AI because we don't have the data," says Cue. "But we have found ways to get that data we need while still maintaining privacy. That's the bottom line."

"We keep some of the most sensitive things where the ML is occurring entirely local to the device," Federighi says. As an example, he cites app suggestions, the icons that appear when you swipe right.

The full-length article on Backchannel provides several more details about how machine learning and artificial intelligence work at Apple.

Popular Stories

AirPods Pro 3 Mock Feature

AirPods Pro 3 Just Months Away – Here's What We Know

Friday April 18, 2025 5:16 am PDT by
Despite being more than two years old, Apple's AirPods Pro 2 still dominate the premium wireless‑earbud space, thanks to a potent mix of top‑tier audio, class‑leading noise cancellation, and Apple's habit of delivering major new features through software updates. With AirPods Pro 3 widely expected to arrive in 2025, prospective buyers now face a familiar dilemma: snap up the proven...
iphone 17 air dummy unbox therapy

iPhone 17 Air's Extreme Thinness Demoed in New Video

Tuesday April 22, 2025 10:22 am PDT by
Apple plans to release an all-new super thin iPhone this year, debuting it alongside the iPhone 17, iPhone 17 Pro, and iPhone 17 Pro Max. We've seen pictures of dummy models, cases, and renders with the design, but Lewis Hilsenteger of Unbox Therapy today showed off newer dummy models that give us a better idea of just how thin the "iPhone 17 Air" will be. The iPhone 17 Air is expected to be ...
ipad air windows 11 arm

M2 iPad Air Runs Windows 11 ARM via Emulation, Thanks to EU Rules

Tuesday April 22, 2025 5:01 am PDT by
A developer has demonstrated Windows 11 ARM running on an M2 iPad Air using emulation, which has become much easier since the EU's Digital Markets Act (DMA) regulations came into effect. As spotted by Windows Latest, NTDev shared an instance of the emulation on social media and posted a video on YouTube (embedded below) demonstrating it in action. The achievement relies on new EU regulatory...
iphone 16 pro models 1

17 Reasons to Wait for the iPhone 17

Thursday April 17, 2025 4:12 am PDT by
Apple's iPhone development roadmap runs several years into the future and the company is continually working with suppliers on several successive iPhone models simultaneously, which is why we often get rumored features months ahead of launch. The iPhone 17 series is no different, and we already have a good idea of what to expect from Apple's 2025 smartphone lineup. If you skipped the iPhone...
iOS 18

iOS 18.5 Includes Only a Few Changes So Far

Monday April 21, 2025 11:00 am PDT by
Apple seeded the third beta of iOS 18.5 to developers today, and so far the software update includes only a few minor changes. The changes are in the Mail and Settings apps. In the Mail app, you can now easily turn off contact photos directly within the app, by tapping on the circle with three dots in the top-right corner. In the Settings app, AppleCare+ coverage information is more...
iphone 17 pro majin bu sky blue

iPhone 17 Pro Allegedly Coming in Sky Blue Color Used for MacBook Air

Tuesday April 22, 2025 4:08 am PDT by
Apple will unveil the iPhone 17 Pro in a new Sky Blue color, the same color that debuted on the latest M4 MacBook Air models Apple released in March. That's according to the leaker Majin Bu. Concept mockup from Majin Bu Writing on his website, Bu claims that "sources close to the supply chain confirm that several iPhone 17 Pro prototypes have been made in various colors, with Sky Blue...
iPhone 17 Pro Blue Feature Tighter Crop

iPhone 17 Pro Launching Later This Year With These 13 New Features

Wednesday April 23, 2025 8:31 am PDT by
While the iPhone 17 Pro and iPhone 17 Pro Max are not expected to launch until September, there are already plenty of rumors about the devices. Below, we recap key changes rumored for the iPhone 17 Pro models as of April 2025: Aluminum frame: iPhone 17 Pro models are rumored to have an aluminum frame, whereas the iPhone 15 Pro and iPhone 16 Pro models have a titanium frame, and the iPhone ...

Top Rated Comments

Santabean2000 Avatar
113 months ago
Siri stills sucks for me... still doesn't work well enough to be useful.
Score: 32 Votes (Like | Disagree)
GfPQqmcRKUvP Avatar
113 months ago
Not in my experience. Siri is absolute trash compared to Google Now and Cortana. Apple should be embarrassed by how stagnant it has been and the repeated, correctable errors it makes. No amount of public relations whitewashing can fix it.
Score: 29 Votes (Like | Disagree)
Oblivious.Robot Avatar
113 months ago
Yeah, no.
Siri is still pretty much useless for me, although better than before, but still meh with her current capabilities.



Edit - For the screen brightness part, after some retries I found out that it does work, but you have to say it in one sentence as Siri forgets about it in the next. :confused:

Attachment Image
Score: 17 Votes (Like | Disagree)
keysofanxiety Avatar
113 months ago
Apple insists that much of the machine learning occurs entirely local to the device, without personal information being sent back to its servers.
And yet it still has no offline functionality, even if the learning is localised; well from what I can see, anyway. An iPhone 3GS managed offline voice functions like "call Tom". Why the heck can't Siri? Phone, text, open an app -- these are not commands that need to be bounced off a server.

It's fine if you're at Apple HQ, testing Siri on a 10Gb/s Internet connection. But when you're on the road with flaky 3G signal, it's the last thing you need.
Score: 11 Votes (Like | Disagree)
jsclem02 Avatar
113 months ago
The struggle with Siri is still very real.

Attachment Image
Score: 11 Votes (Like | Disagree)
thisisnotmyname Avatar
113 months ago
I like Siri on the iPhone when it works, but at times it totally gets things very wrong that it previously got right.

What really gets me ticked off is how Siri on ATV is worse than useless almost every time I try to make use of it.
I agree. On the phone she works well for me. On the AppleTV it seems like she goes to sleep and the first time I try to interact with her such as "what did he just say?" it lags so long that the ten second rewind is well past whatever I wanted to hear. And then there's the lack of Siri search through home sharing content...
Score: 7 Votes (Like | Disagree)