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

Amazon Lex – Build Conversational Voice and Text Interfaces

aws.amazon.com

Post reply on HN
Print view View original

41–50 of 56 posts

Re: Amazon Lex – Build Conversational Voice and Text Interfaces

#41

Post by flukus »

djyaz1200 wrote: post #21

Seems like these chat bots have A LOT of lock in. So the question is which one to pick? This one? IBM Watson? Others? Which horse are you betting on and why? Amazon making this is great because it's developer friendly and will surely fall in price and improve in quality over time. They also have to make it work well because it's a critical ordering channel for them going forward. Seems like IBM has been focused on th…

> Seems like these chat bots have A LOT of lock in. So the question is which one to pick? This one?

None of the above? We had desktop voice to text 20 years ago (that was about on par with google now for me) so I don't see why everything has to go through cloud services.

Re: Amazon Lex – Build Conversational Voice and Text Interfaces

#42

Post by digital_ins »

chishaku wrote: post #3
dominotw wrote: post #2

>you know how simple, useful, and powerful the Alexa-powered interaction model can be. This is so comical. Alexa is phenomenally bad at conversation, it is so bad that there are almost no successful "apps" built around it despite having an API and app platform. Alexa is decent at single command/action model nothing more than that.

What are the best alternatives?

This, for travel, for example: https://www.youtube.com/watch?v=s_kw_vlCpcw

Disclosure: I work at the co that builds this

Re: Amazon Lex – Build Conversational Voice and Text Interfaces

#43

Post by choxi »

olavgg wrote: post #35
djyaz1200 wrote: post #21

Seems like these chat bots have A LOT of lock in. So the question is which one to pick? This one? IBM Watson? Others? Which horse are you betting on and why? Amazon making this is great because it's developer friendly and will surely fall in price and improve in quality over time. They also have to make it work well because it's a critical ordering channel for them going forward. Seems like IBM has been focused on th…

I'm working for a startup called Boost.ai where we have decided to build our own deep learning model and create our own training data. We use several models that predicts what word comes next, take care of mispellings and dialects. We also have memory so it can remember contexts when you ask a new question or it predicts that you want to start with a new context. If you want something kick ass, I highly recommend bui…

Any pointers on where to get started? I've messed with Karpathy's RNN example using Shakespeare and PG essays, but don't know where to go from there.

Re: Amazon Lex – Build Conversational Voice and Text Interfaces

#44

Post by chiefalchemist »

ronack wrote: post #24
djyaz1200 wrote: post #21

Seems like these chat bots have A LOT of lock in. So the question is which one to pick? This one? IBM Watson? Others? Which horse are you betting on and why? Amazon making this is great because it's developer friendly and will surely fall in price and improve in quality over time. They also have to make it work well because it's a critical ordering channel for them going forward. Seems like IBM has been focused on th…

You're right, lack of standardization and portability is a major problem. I would not personally choose IBM due to the pricing model and previous bad experiences. Google, Microsoft, and Facebook (and a bunch of startups) have all built or acquired conversational services very much like Lex. None of them is a clear winner at this point in my opinion.

Call me naive/stupid but how is this any different than a backend DB? Can't an interface prevent any sorta lock in?

Re: Amazon Lex – Build Conversational Voice and Text Interfaces

#45

Post by chiefalchemist »

olavgg wrote: post #35
djyaz1200 wrote: post #21

Seems like these chat bots have A LOT of lock in. So the question is which one to pick? This one? IBM Watson? Others? Which horse are you betting on and why? Amazon making this is great because it's developer friendly and will surely fall in price and improve in quality over time. They also have to make it work well because it's a critical ordering channel for them going forward. Seems like IBM has been focused on th…

I'm working for a startup called Boost.ai where we have decided to build our own deep learning model and create our own training data. We use several models that predicts what word comes next, take care of mispellings and dialects. We also have memory so it can remember contexts when you ask a new question or it predicts that you want to start with a new context. If you want something kick ass, I highly recommend bui…

Re: "If you want something kick ass, I highly recommend building it yourself."

That might be true, but the ability to spin something up without all that overhead is any MVP'ers wet dream, yes?

Re: Amazon Lex – Build Conversational Voice and Text Interfaces

#46

Post by sprobertson »

mtthwmtthw wrote: post #39

Are there any open source project like this? I would imagine it's a machine learning model to match intent and then a custom NER that extracts slots. I'm sure the actual models are pretrained on lots of data, and the process is probably a lot more complex. Given the abundance of vendors in this space, it has to at least be a possibility .

For very simple human language to intent parsing (no prompting or context keeping), here's a RNN model in Torch that learns intents and slots based on a bunch of template sentences: https://github.com/spro/intense

Re: Amazon Lex – Build Conversational Voice and Text Interfaces

#47

Post by squidbot »

hackcrafter wrote: post #22

This is neat but I've been on the lookout for a service that takes speech and responds with speech that you can use in a domain-specific app. Basically, Alexa as a service? Is there something out there that does this? For certain things that require hands-free usage, this would be a killer feature. ex. a workout-app that tells you your next rep and weight, and you can respond with what weight/reps you did to add to y…

You could pair https://developer.amazon.com/alexa-voice-service with https://developer.amazon.com/alexa-skills-kit

Re: Amazon Lex – Build Conversational Voice and Text Interfaces

#48

Post by smiled0g »

flukus wrote: post #41
djyaz1200 wrote: post #21

Seems like these chat bots have A LOT of lock in. So the question is which one to pick? This one? IBM Watson? Others? Which horse are you betting on and why? Amazon making this is great because it's developer friendly and will surely fall in price and improve in quality over time. They also have to make it work well because it's a critical ordering channel for them going forward. Seems like IBM has been focused on th…

> Seems like these chat bots have A LOT of lock in. So the question is which one to pick? This one? None of the above? We had desktop voice to text 20 years ago (that was about on par with google now for me) so I don't see why everything has to go through cloud services.

I don't think desktop solutions (like Microsoft speech synthesizer) does a great job at producing "natural" and life-like speeches. Sure, it does read the text, but that's about it.

To properly produce speech, the synthesizer needs to take into account context of around words to determine how to pronounce ambiguous words or how to pace the speech. What about the tone? How about making the speech sounds more engaging? These are the things that need data model to work great. However, it's just difficult to cram that into a desktop app. And why would any company do that when they can put the service online and charge for it (which is totally fair)?

Re: Amazon Lex – Build Conversational Voice and Text Interfaces

#49

Post by flukus »

smiled0g wrote: post #48
flukus wrote: post #41

Earlier quoted context omitted.

> Seems like these chat bots have A LOT of lock in. So the question is which one to pick? This one? None of the above? We had desktop voice to text 20 years ago (that was about on par with google now for me) so I don't see why everything has to go through cloud services.

I don't think desktop solutions (like Microsoft speech synthesizer) does a great job at producing "natural" and life-like speeches. Sure, it does read the text, but that's about it. To properly produce speech, the synthesizer needs to take into account context of around words to determine how to pronounce ambiguous words or how to pace the speech. What about the tone? How about making the speech sounds more engaging?…

I was thinking more about the other way because that's the hard part, we can understand synthesized voices better than they can understand us.

Apple seems far and away the best desktop solution. For other OS's though, it's frustrating that they haven't improved on what computers of the early eighties could do. Now you've made me nostalgic though, I'll never forget the first time I heard my amiga 500 read my words.

Re: Amazon Lex – Build Conversational Voice and Text Interfaces

#50

Post by 83457 »

david927 wrote: post #30
83457 wrote: post #17

Earlier quoted context omitted.

In intro to comp sci we had an open project using an irobot bot (roomba without vaccum) so my group of some of the more experienced students pieced together a robot dog using a laptop and xbox kinect on top. You could say commands and it would obey such as sit (moves back and stops), rollover (spins), bark (sound from speakers), etc. It would also track a primary user and if you said follow it would stay a certain di…

That sounds great! You should post a video of it. Personally, I was thinking of something cheaper, such as a Raspberry Pi with a stepper motor.

unfortunately I didn't get video (as silly as that sounds) and the person who did never sent to me

I even put my son's furry dog halloween costume on it :)

Post reply on HN