Funny ad
Jarvis: an Amazon Echo clone in your browser
71–79 of 79 posts
Re: Jarvis: an Amazon Echo clone in your browser
#72Yeah 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.…
actually somebody even cross-compiled pocketsphinx to javascript with emscripten for this purpose:
https://syl22-00.github.io/pocketsphinx.js/live-demo.html
this works pretty well - all in the browser, especially if you drop in some better acoustic models.
Re: Jarvis: an Amazon Echo clone in your browser
#73What is the current state of offline, non-cloud-connected speech-to-text? My phone has a voice processing chip, and it recognizes my speech pretty well, but I still can't figure out if it's completely disconnected from the cloud (despite intentionally not agreeing to the privacy policy) His demo is just a shim for Amazon's API...
> My phone has a voice processing chip, and it recognizes my speech pretty well, but I still can't figure out if it's completely disconnected from the cloud Does it work when you are in airplane mode?
It does.
There's an offline language pack installed, though.
Re: Jarvis: an Amazon Echo clone in your browser
#74Earlier 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.
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.
Reminds me of the coding horror post, "Code: It's trivial" http://blog.codinghorror.com/code-its-trivial/
Re: Jarvis: an Amazon Echo clone in your browser
#75Earlier quoted context omitted.
Not that I've found yet, but the actual hardware on that board costs something like $10-15, so someone could easily make one. The high price is because it's a development board. (I think it's a silly to price development boards highly, but it is very common.)
I'm curious, how would you recommend they be priced?
Every comment that starts with "curious" seem to be spam on HN. Is this always the same guy or a bot? Almost every HN topic contains one of these "curious" comments...
Re: Jarvis: an Amazon Echo clone in your browser
#76Earlier quoted context omitted.
I'm curious, how would you recommend they be priced?
Every comment that starts with "curious" seem to be spam on HN. Is this always the same guy or a bot? Almost every HN topic contains one of these "curious" comments...
It's a common English idiom, but even though I've been here over twice as long as your account date I can't say I've noticed an infestation of "curious" comments... though given curiosity is a hacker virtue, perhaps it's not surprising there may be more of it here? I still am genuinely curious how GGP would have dev boards priced instead -- the market is pretty much limited to students (the ones at good schools have the schools pay for the boards, or the schools get discounts) or professionals (who again expense through their company), what's the incentive to lower prices?
Re: Jarvis: an Amazon Echo clone in your browser
#77Earlier quoted context omitted.
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.…
actually somebody even cross-compiled pocketsphinx to javascript with emscripten for this purpose: https://syl22-00.github.io/pocketsphinx.js/live-demo.html this works pretty well - all in the browser, especially if you drop in some better acoustic models.
Yeah I wouldn't call that "pretty well" - I said "not a number" and it outputted "one two one" on the digits example.
Maybe it just wasn't trained well enough to reject non-number inputs, but.. yeah doesn't exactly change my experience that Sphinx is awful.
Re: Jarvis: an Amazon Echo clone in your browser
#78Earlier quoted context omitted.
actually somebody even cross-compiled pocketsphinx to javascript with emscripten for this purpose: https://syl22-00.github.io/pocketsphinx.js/live-demo.html this works pretty well - all in the browser, especially if you drop in some better acoustic models.
Yeah I wouldn't call that "pretty well" - I said "not a number" and it outputted "one two one" on the digits example. Maybe it just wasn't trained well enough to reject non-number inputs, but.. yeah doesn't exactly change my experience that Sphinx is awful.
You have to use a decent acoustic model - not the one in the demo. If you do I think it works 'pretty well' as a proof of concept. That said I'm not recommending Sphinx as a recognition framework, it is way behind the times in 2016, but this is the only 'in the wild' demo of this I've seen on the web, so I felt it was worth mentioning.
Re: Jarvis: an Amazon Echo clone in your browser
#79Does anyone know how the Google TTS voices in the example are exposed by Google? Is there an API / service for these? I haven't been able to find it. I was able to use them on PageNodes via the "espeak" output just fine, but would like to use them directly in my own apps.
This might help you: https://github.com/monteslu/pagenodes/blob/7388ce58726836cf6...
Super helpful. Thanks!
In Chrome the following works as a basic sample:
speech = new SpeechSynthesisUtterance(String("生日快乐"))
voice = speechSynthesis.getVoices()[80] // use Google Chinese Voice
speech.voice = voice
speechSynthesis.speak(speech)