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

Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

stonetemple.com

Post reply on HN
Print view View original

41–50 of 172 posts

Re: Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

#41

Post by SuperKlaus »

inopinatus wrote: post #15
masterjack wrote: post #10

Oh awesome, let's see... how many atoms are there in the universe? "The number of atoms in the entire observable universe is estimated to be within the range of 1078 to 1082." Thank you Google! http://www.google.com/search?q=how+many+atoms+are+in+the+uni... ]

Try it on Wolfram Alpha. Actually, they all seem to me pretty limited compared to the answers you get from Wolfram Alpha. Also c.f. the responses to one of their test questions, "how much is a quarter cup of butter?". Google makes fun of the inquiry. Wolfram Alpha gives you a thorough nutritional profile, and links to variations based on international cup sizing and different types of butter.

I just learned that Canadian cups != American cups. (227g vs 218g) Who would have thought....

Re: Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

#42

Post by syllogism »

walterbell wrote: post #17

Who owns the key patents for voice recognition - AT&T, Nuance, IBM? When will they be expire and be available for use in open-source speech recognition? Edit: some data at http://www.quora.com/Is-anyone-working-on-an-open-source-ver... & https://news.ycombinator.com/item?id=4987875

Actually I think most of the work has been done in academia --- certainly that's where the recent deep learning stuff has come from. So, I don't think the important stuff is patented. (In general it's very hard to lock down ML improvements under patent. Once we can do it one way, and understand a little bit about what's working, we can usually replicate that performance with another technique.)

The big problem for open source speech recognition is training data.

Re: Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

#43

Post by b2themax »

bphogan wrote: post #30
b2themax wrote: post #9

FWIW, I just switched from Windows Phone to iOS -- from the 1020 to iPhone6+. Personally, I preferred Cortana over Siri. And it basically comes down to speed and responsiveness. Cortana is much quicker to launch, and much quicker to find results. I haven't noticed any discernable difference in their query results. And actually, for one of the my most used queries - "What is the weather today?" -- I dont even use it o…

That's really interesting to me, because my daughter (6yo) asks Siri that question about 10 times a day on the 5S and the answer comes back in about a second. Whether we're on LTE or wifi. I wonder if there's other factors at play.

I believe Cortana would get that info back in less than a second. It seems Siri takes more than a second for me just to activate, before it even begins listening... Maybe this is an iOS 8 issue for the time being...?

Re: Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

#44

Post by arjie »

HelloMcFly wrote: post #34
rayiner wrote: post #29

I think this analysis is kind of pointless. Who asks their phone trivia questions? You want directions, reminders, etc. Siri seems a lot smarter about following spoken context in that situation.

I can't speak extensively for Siri (infrequent use on my iPad) or Google Now (no Android), but I've never had to repeat an instruction to Cortana for a reminder or directions. Not repeating myself when giving voice instruction is essentially my holy grail.

That is, indeed, fantastic. Does it hold context? I mean, can you say "Find a gas station." and then "Find a McDonald's near that" and have it work? That would be super.

Re: Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

#45

Post by joshschreuder »

bane wrote: post #12
w-ll wrote: post #3

Slightly OT, but in school I remember a teach talking about how good voice to text has gotten but was stuck, stating it was roughly about a 70% accuracy, but that we were pretty much at a wall there and haven't moved much in the last decade. Has there been any major advances in voice recognition other than just growing your speech corpus?

I've actually taken to dictating most of my texts on Android. It's faster for me than typing or swype-style keyboards and it's really very accurate until I need to use a strange proper name it doesn't understand. I'd say it easily gets about 90% of what I say, and it figures out the correct context for words like "there" "their" "they're" and "to" and "too" so far completely correct. edit thought I'd add this. I just…

How do you write text messages in private and not have your messages overheard? I think I would be quite self concious that I'm talking into my phone and not directing it at anyone (I rarely use Siri for this reason)

Re: Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

#46

Post by modfodder »

kumarm wrote: post #18
aresant wrote: post #5

The article concludes that google is dramatically ahead, which is no suprise but I AM suprised, anecdotally, how good Siri is vs previous iterations on my iphone 6 and OS 8 It feels close to "good enough" for the majority of functions I actually use eg: dictate an email, get directions, lookup a contact, and dial a phone number. My sense is that Apple will nail the base functions so that most users, self included, wo…

50% is good enough if its done by Apple. 90% not good enough if its not done by Apple. This is how I interpret most responses when people talk about Apple.

Well, as accurate as I feel your statement is, I'd also say sometimes it depends on the 10% missing from the products not done by Apple. If it's an important 10% that Apple has nailed (or close enough) then sometimes the 50% is more valuable than the 90%.

But we all have our biases as well. (Even as an Apple user I fully expect Google to always win the Knowledge Vault race. Its in their wheelhouse more so than Apple's.)

Re: Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

#47

Post by melling »

syllogism wrote: post #42
walterbell wrote: post #17

Who owns the key patents for voice recognition - AT&T, Nuance, IBM? When will they be expire and be available for use in open-source speech recognition? Edit: some data at http://www.quora.com/Is-anyone-working-on-an-open-source-ver... & https://news.ycombinator.com/item?id=4987875

Actually I think most of the work has been done in academia --- certainly that's where the recent deep learning stuff has come from. So, I don't think the important stuff is patented. (In general it's very hard to lock down ML improvements under patent. Once we can do it one way, and understand a little bit about what's working, we can usually replicate that performance with another technique.) The big problem for op…

First, these are two different problems to solve. Voice recognition and deep learning are different fields.

Is training really the issue for voice recognition? It has been a problem that has almost been solved for over a decade. Last year I saw this impressive use of Dragon Naturally Speaking for the PC, running in a VM on a Mac, that pretty much worked to code by voice.

https://www.youtube.com/watch?v=8SkdfdXWYaI

The developer mentioned that he didn't have any luck with Sphinx.

Xah Lee summarized the talk here: http://ergoemacs.org/emacs/using_voice_to_code.html

Re: Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

#48

Post by walterbell »

syllogism wrote: post #42
walterbell wrote: post #17

Who owns the key patents for voice recognition - AT&T, Nuance, IBM? When will they be expire and be available for use in open-source speech recognition? Edit: some data at http://www.quora.com/Is-anyone-working-on-an-open-source-ver... & https://news.ycombinator.com/item?id=4987875

Actually I think most of the work has been done in academia --- certainly that's where the recent deep learning stuff has come from. So, I don't think the important stuff is patented. (In general it's very hard to lock down ML improvements under patent. Once we can do it one way, and understand a little bit about what's working, we can usually replicate that performance with another technique.) The big problem for op…

> The big problem for open source speech recognition is training data.

What exactly is needed for training - audio recordings with transcripts, human validation of recognized text?

There are successful crowdsourced efforts for proofreading of OCR'ed text. Archive.org could host a CC-licensed archive of sound & transcripts.

Recognition of the human voice is almost like writing, hopefully everyone could have access.

Edit: how much disk space would be needed - TB or PB?

Re: Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

#49

Post by walterbell »

melling wrote: post #47
syllogism wrote: post #42

Earlier quoted context omitted.

Actually I think most of the work has been done in academia --- certainly that's where the recent deep learning stuff has come from. So, I don't think the important stuff is patented. (In general it's very hard to lock down ML improvements under patent. Once we can do it one way, and understand a little bit about what's working, we can usually replicate that performance with another technique.) The big problem for op…

First, these are two different problems to solve. Voice recognition and deep learning are different fields. Is training really the issue for voice recognition? It has been a problem that has almost been solved for over a decade. Last year I saw this impressive use of Dragon Naturally Speaking for the PC, running in a VM on a Mac, that pretty much worked to code by voice. https://www.youtube.com/watch?v=8SkdfdXWYaI Th…

Thanks for that pointer to the Python library which integrates with Dragon/Nuance to enable arbitrary commands, https://pypi.python.org/pypi/dragonfly/

Re: Google Now vs. Siri vs. Cortana – The Great Knowledge Box Showdown

#50

Post by msoad »

Some query patterns I use in Google that you might be interested in

    Translate {words} to {language}
    My flights
    My schedule
    My packages
    What time is at {city}?
    How tall/old/heavy is {important person}?
    {description of a photos} in my photos (like 'ocean in my photos')
    Note: if you have G+ photos. description doesn't need to be typed in the photo meta info
    compare {food} and {food} (nutritions)
Post reply on HN