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

How Alexa knows “peanut butter” is one shopping-list item, not two

developer.amazon.com

Post reply on HN
Print view View original

121–130 of 147 posts

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#121

Post by coldtea »

huffmsa wrote: post #67
grecy wrote: post #63

Earlier quoted context omitted.

> A better question is "coconut, milk" versus "coconut milk". Sure, but if you were dictating to a human that would still be an easy one for them to get wrong, depending on how long you paused. I find this interesting with phone numbers. In some countries you hear people say "thirty three sixty two" and they mean 303602

And that's what makes it interesting. Peanut butter versus peanuts, butter is easy. No one gets a single peanut. As for the phone number, that's why anyone in a serious occupation (aviation, military, etc) treat each digit as is stand-alone. Three-zero-three-six-zero-two.

>No one gets a single peanut

You'd be surprised: https://www.youtube.com/watch?v=HoPFQm9PQ_M

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#122

Post by master_yoda_1 »

tacomonstrous wrote: post #113
smoser wrote: post #95

Amazon is pulling ahead. Siri still adds 'All man milk' to my shopping list instead of almond milk.

Siri has been behind Google and Alexa basically since the beginning and shows little sign of catching up.

This article say it all https://www.theinformation.com/articles/the-seven-year-itch-...

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#123

Post by cr0sh »

coldtea wrote: post #117
jchw wrote: post #62

Earlier quoted context omitted.

Sentences spoken aloud don't have commas.

You don't need commas to do that in text parsing either. Newlines, for example, will do. When spoken, a shopping list is not a sentence. There's a small pause and/or different emphasis on the start of each item that can be learned (humans, for one, can discern it). "Eggs milk peanut-butter" sounds different than "Eggs milk peanut butter". (Besides it can easily learn that peanut, singular, is not a thing people order…

> "Eggs milk peanut-butter" sounds different than "Eggs milk peanut butter"

True, but I've never went to the grocery store to buy a singular peanut.

I've bought a bag of peanuts, but not just one peanut.

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#124

Post by 8bitsrule »

jchw wrote: post #62
NicoJuicy wrote: post #49

In text parsing, this whole machine learning would be implemented as "ignore white space as delimiter" ( that's how I implemented it on one of my projects) Ps. I'm aware this will not be a popular comment

Sentences spoken aloud don't have commas.

OK, bullets then. At any rate ... a one-line of code solution is a flimsy excuse for a product placement.

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#125

Post by stan_rogers »

qlm wrote: post #59
xioxox wrote: post #53

Earlier quoted context omitted.

I'm not convinced. It takes effort for me to break apart blackbird into two separate words in my head, as they are so commonly found together. When speaking "black bird" I would insert a long pause between the two and emphasise the "b" on bird to show that I'm not talking about a "blackbird".

The difference for me (maybe this is regional?) is that for “blackbird” the stress is on “black” whereas for “black bird” the stress is on “bird”.

Yes, it's mostly about the stress.

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#126

Post by cecilpl2 »

cr0sh wrote: post #123
coldtea wrote: post #117

Earlier quoted context omitted.

You don't need commas to do that in text parsing either. Newlines, for example, will do. When spoken, a shopping list is not a sentence. There's a small pause and/or different emphasis on the start of each item that can be learned (humans, for one, can discern it). "Eggs milk peanut-butter" sounds different than "Eggs milk peanut butter". (Besides it can easily learn that peanut, singular, is not a thing people order…

> "Eggs milk peanut-butter" sounds different than "Eggs milk peanut butter" True, but I've never went to the grocery store to buy a singular peanut. I've bought a bag of peanuts, but not just one peanut.

Eggs milk avocado-oil

Eggs milk cheese-buns

Eggs milk chicken-salad

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#127

Post by jchw »

coldtea wrote: post #119
jchw wrote: post #76

Earlier quoted context omitted.

That was not the point of what I said at all. It Could interpret the vocal cues, yes. As far as I know this is still not a solved problem for speech to text, and results going the other way and trying to guess punctuation is still more reliable. Back to what I really was getting at: I'm pretty sure the person I replied to was suggesting Alexa could just split(',') and call it a day. With text, yes. With voices this w…

> As far as I know this is still not a solved problem for speech to text Understanding pauses/inflection changes doesn't have to be a "solved problem" to work for cases such as discerning common shopping list style items. With voices this would be irritatingly unreliable. Everyone talks differently and sometimes people stumble weirdly. That's an argument against discerning "milk" from "silk" or "coke" from "cork", bu…

>Understanding pauses/inflection changes doesn't have to be a "solved problem" to work for cases such as discerning common shopping list style items.

Okay... But Alexa isn't just shopping lists. You only know you are dealing with a shopping list after parsing the text.

Even if you did go back, is the narrower use case any more solved than the general one? Guessing with text alone turns out to be fairly accurate and so even if you could do this decently, it would have to be notably better to be worth the trouble.

>That's an argument against discerning "milk" from "silk" or "coke" from "cork", but that's still managed satisfactorily enough.

Irrelevant to this though, considering that problem has mostly been solved at this juncture.

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#128

Post by jchw »

8bitsrule wrote: post #124
jchw wrote: post #62

Earlier quoted context omitted.

Sentences spoken aloud don't have commas.

OK, bullets then. At any rate ... a one-line of code solution is a flimsy excuse for a product placement.

I don't understand. You realize the speech recognition algorithm gives you raw words with no punctuation, right?

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#129

Post by avip »

cecilpl2 wrote: post #126
cr0sh wrote: post #123

Earlier quoted context omitted.

> "Eggs milk peanut-butter" sounds different than "Eggs milk peanut butter" True, but I've never went to the grocery store to buy a singular peanut. I've bought a bag of peanuts, but not just one peanut.

Eggs milk avocado-oil Eggs milk cheese-buns Eggs milk chicken-salad

  pudding pudding pudding applesauce
  pudding pudding pudding applesauce
  pudding pudding pudding applesauce
  applesauce applesauce applesauce

Re: How Alexa knows “peanut butter” is one shopping-list item, not two

#130

Post by pbhjpbhj »

chrisfosterelli wrote: post #118
pbhjpbhj wrote: post #109

Earlier quoted context omitted.

This. I'd assume it's like "creamer" which is a fake milk substitute from USA I think? But, it could be coffee flavoured cream; or "coffee creams" which are biscuits in the UK, or maybe some sort of confection? Yeah, I should just look it up ...

"coffee cream" AKA "half and half" in much of the US or "half cream" in the UK

I (native UK) have never heard of "half cream", is that like "single cream"?
Post reply on HN