Live data from Hacker News

Jarvis: an Amazon Echo clone in your browser

iceddev.com

61–70 of 79 posts

Re: Jarvis: an Amazon Echo clone in your browser

#61

Earlier quoted context omitted.

$750 for the mic?!? ( http://www.xmos.com/buy?product=20258 )

Development kits are expensive due to low sales volume, no cost optimization, and buyers' price insensitivity. There is a huge amount of value in having a known good implementation on hand when designing hardware or firmware. Additionally, having the development kit means your firmware team can start developing before your hardware arrives. If you have a good relationship with them, sales reps will often give or lend…

Thx :)

My comment was more about the parent's comment of it being "a real clone" when a Dot is 1/8th the price of this.

Re: Jarvis: an Amazon Echo clone in your browser

#62
post #58
post #11

Earlier quoted context omitted.

Even if true, not sure why you wrote such a snarky comment. This obviously is a side project of the author and just serves as an inspiration, it's not like he is asking money for it or anything.

It is PR to sell one of their products

It's open source :) https://github.com/monteslu/pagenodes

Re: Jarvis: an Amazon Echo clone in your browser

#63
post #21

Earlier quoted context omitted.

wow, that microphone array you linked costs USD$750! Are there any cheaper alternatives?

I think the Microsoft Kinect comes with a Microphone Array.

Yes Kinect has an array of 4 mics and can do audio beam forming. Plus there's a terrific SDK for Windows.

Re: Jarvis: an Amazon Echo clone in your browser

#64
post #3

Yeah it's a clone of the trivial parts of the Echo, but not the difficult parts that are necessary to make it great, specifically: * Beamforming microphone array (this is a real clone: http://www.xmos.com/products/microphones ) * Wake-word / hot-word detection ("Ok Google", "Alexa", etc.) * Intent recognition / NLU

I'm guessing that XCore product is well out of the price range of hobbyists, which is unfortunate.

Re: Jarvis: an Amazon Echo clone in your browser

#65
post #21

Earlier quoted context omitted.

wow, that microphone array you linked costs USD$750! Are there any cheaper alternatives?

I think the Microsoft Kinect comes with a Microphone Array.

I said it in a thread about the Kinect - I think it's only 135 (ish) degrees of reception, and sometimes it can be more finicky than that.

I'd love to get my hands on an open source array.

Re: Jarvis: an Amazon Echo clone in your browser

#66
post #3

Yeah it's a clone of the trivial parts of the Echo, but not the difficult parts that are necessary to make it great, specifically: * Beamforming microphone array (this is a real clone: http://www.xmos.com/products/microphones ) * Wake-word / hot-word detection ("Ok Google", "Alexa", etc.) * Intent recognition / NLU

Even that XMos dev kit won't give you all you need for the beam-forming part of the microphone array: "Customer adds own DSP to create differentiated product" The DSP is where you'd implement the beam-forming algorithm to get one clear audio stream rather than 8...

Re: Jarvis: an Amazon Echo clone in your browser

#67
post #3

Yeah it's a clone of the trivial parts of the Echo, but not the difficult parts that are necessary to make it great, specifically: * Beamforming microphone array (this is a real clone: http://www.xmos.com/products/microphones ) * Wake-word / hot-word detection ("Ok Google", "Alexa", etc.) * Intent recognition / NLU

Some of that stuff isn't too hard, if you can narrow down the domain of words you need to recognize. For example, let's say you wanted to have a hot word of "computer", like in star trek, you can literally filter the output of the recognizer (e.g. pocketsphinx) with grep and sed and it works not too badly. For the natural language part, you can get pretty far with a simple parser like the old infocom games used, esp. if your domain is limited. I'm making an open source multiplayer networked starship bridge simulator, kind of like star trek, using pocketsphinx for speech recognition, and it's working ok (not perfect, but ok.) Here is a demo: https://www.youtube.com/watch?v=tfcme7maygw

Re: Jarvis: an Amazon Echo clone in your browser

#68
post #11
post #3

Yeah it's a clone of the trivial parts of the Echo, but not the difficult parts that are necessary to make it great, specifically: * Beamforming microphone array (this is a real clone: http://www.xmos.com/products/microphones ) * Wake-word / hot-word detection ("Ok Google", "Alexa", etc.) * Intent recognition / NLU

Even if true, not sure why you wrote such a snarky comment. This obviously is a side project of the author and just serves as an inspiration, it's not like he is asking money for it or anything.

I will say, I find the trend of HN posts that say "clone" of some commercial product but are missing significant features to be kind of frustrating. It tends to devalue the work that's actually involved in creating successful projects - and thus the work of software engineering.

Re: Jarvis: an Amazon Echo clone in your browser

#69
post #3

Yeah it's a clone of the trivial parts of the Echo, but not the difficult parts that are necessary to make it great, specifically: * Beamforming microphone array (this is a real clone: http://www.xmos.com/products/microphones ) * Wake-word / hot-word detection ("Ok Google", "Alexa", etc.) * Intent recognition / NLU

It does have wake word detection, and even has that code right there in the article. It matches on jarvis/nervous/service/travis as the first word in the phrase, because those are the words that get returned by the speech recognition when he says 'jarvis'.

That ambiguity in hotword detection makes me nervous.

Re: Jarvis: an Amazon Echo clone in your browser

#70
post #40

This article is a bit out of my comfort zone (I'm not a web app developer), however it does link to a GitHub repository by Amazon, that I was unaware of, which shows how to configure a Raspberry Pi as an Echo clone in quite a lot of detail. This is something I can do and have bookmarked it for a rainy day. So for that alone, thanks for the submission!

Here's the previous HN discussion on that [0]. Keep in mind that the DIY Echo project doesn't support "always-listening" with a wake word, but instead you have to press a button to activate the voice-control. Not really that inconvenient though, and some people do prefer a button to something always listening. [0] https://news.ycombinator.com/item?id=11362460

Thanks!
Post reply on HN