Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Speech to Text on iPhone vs. Pixel

twitter.com

Post reply on HN
Print view View original

51–60 of 131 posts

Re: Speech to Text on iPhone vs. Pixel

#51

Post by xenospn »

jonplackett wrote: post #16
ksec wrote: post #13

Well the iPhone is doing this online. While Pixel is doing it offline. Which is why the latency difference. ( Specific to English only, some languages still requires connection on Pixel ) I think dictation on iPhone is good enough, at least 10 times better than pre iPhone / Machine learning era. But it is also not as good as google. Partly because Google has more Data and started research way earlier, and partly beca…

That just makes it even worse! Look how much better the Pixel is doing on accuracy too. It's almost flawless while the iPhone, despite the advantage of offline processing, is getting maybe 10% wrong and writing complete nonsense words in there. Who is the hell is "Poor Michael Geer"? (for clarity, I'm an iPhone user and won't be switching because privacy, but this makes me jealous)

I keep trying to dictate text messages to my iphone while driving and it keeps driving me nuts. Not usable.

Re: Speech to Text on iPhone vs. Pixel

#53

Post by ChrisClark »

oh_hello wrote: post #39

An an iPhone user, I very often find speech recognition far too slow. It is to the point I rarely use the feature because it often causes frustration. The Google performance here is amazing. Is this a feature only of Pixel phones?

I just tested on my old OnePlus 5t, I find it's slower than the Pixel in this video, but still much faster than the iPhone.

It's not unique to the Pixel, it's just that it's a faster phone than my 5t.

But even though it's just a little slower than the Pixel, it makes a big difference. The closer it is to real-time, it seems to get so much better.

Re: Speech to Text on iPhone vs. Pixel

#54

Post by lern_too_spel »

willis936 wrote: post #24
nods wrote: post #23

Earlier quoted context omitted.

Why do you say: "I use iPhones for the same privacy concerns as many of you"? In the past I have heard rumors that is not true, with a quick search I found out a recent article on the rumors that I heard once: https://www.forbes.com/sites/gordonkelly/2020/05/21/apple-ip... PS: Either way, I agree with most of your comment. :)

Because the alternative is Android, which is very difficult to de-Google. Even if you do de-Google you need to open yourself up to a swath of security concerns. Why would I trust some internet account that is giving me a binary that compromises my phone for me? Should I trust that it will only do what they say it will do because they are a good person? Would they have nothing to gain for having complete control of my…

iOS having better privacy is a myth. iOS sends your location to Apple every time any the GPS is used, and you can't turn it off. You cannot install apps on your phone without telling Apple which apps they are, and if you want to develop your own apps for your device without having to reinstall weekly, you have to hand over payment information.

Stock Android devices from nearly any vendor do not suffer from these problems, and reputable vendors do even better (like in this case, where even voice transcription does not send data off device).

Re: Speech to Text on iPhone vs. Pixel

#55

Post by anchpop »

jonplackett wrote: post #45

QUESTION How hard, on a scale of 1 to impossible, how hard would it be for Apple, or someone else to just grab the model google is using from the pixel and reverse engineer it and steal all their years of research.

It would probably be easy for any on-device model. But it would be illegal

Re: Speech to Text on iPhone vs. Pixel

#57

Post by garaetjjte »

cl0rkster wrote: post #4

There are already some novel applications of this. It is extremely useful to use Google's screening service for unknown numbers that might be a call I'm expecting from a new number. I can't recall the last time I actually listened to a voicemail. I know that at least voicemail transcription works elsewhere, and I can't speak to how well, but I do know that on the Pixel, transcription is really quite impressively accu…

Is voicemail popularity some US thing? I actually don't know anybody who uses it.

Re: Speech to Text on iPhone vs. Pixel

#58

Post by gregsadetsky »

I have an extension in the Chrome store [0] that brings dictation into GMail. I piggyback on the Web Speech API, which in the case of Chrome uses Google's servers.

Considering the audio stream upload & processing & network jitter/lag, the speed at which text results come back is simply incredible. I don't remember the exact timing, but it was a roundtrip of 40-100?ms which is... crazy/magic.

I made a small experiment with this same Chrome text to speech engine which triggered a google image search and showed in near real time image results for the spoken words. The slowest part of that Rube Goldberg was the google images search + loading the images. [1]

I also.... "secretly" believe that very fast speech recognition is one of "the" secrets to building a smarter / better digital voice assistant. It's one of the key components (with a ton of groundbreaking NLP and/or the right regexes) that might allow closing the "strange feeling" you get when talking to the robot... voice... and... it... answers....... not ... exactly when...... you were expecting it.... to.

I'm super mega busy these days but also super mega interested in this. Reach out? :-)

[0] https://chrome.google.com/webstore/detail/dictation-for-gmai...

[1] https://www.instagram.com/p/BwqFQgWFsYu/

Re: Speech to Text on iPhone vs. Pixel

#59

Post by mwest217 »

kccqzy wrote: post #56

In case anyone didn't notice, this is comparing Gboard (Google's virtual keyboard) on iOS versus Android. It's NOT comparing Apple's voice recognition tech with Google's.

That's actually (sneakily) not the case. Gboard does have voice transcription, but it's triggered by pressing the microphone button at the upper right corner of the keyboard. Apple's voice transcription is still triggered from the bottom right button, even if a 3rd party keyboard is being used.

Re: Speech to Text on iPhone vs. Pixel

#60

Post by m0zg »

And Apple could literally do this faster than Google due to much better onboard hardware. They're just years behind at AI at this point. It's getting embarrassing. Some _individual researchers_ can do a better job than their entire speech-to-text team is doing here.

Although to me, neither example is useful without:

1. Automatic punctuation

2. Robust recognition in noisy environments

And neither system is capable of that yet, although Google's system is better at #2.

Post reply on HN