Siri-as-a-Service Speech API
AI
speech recognition api
SHOW HN2014
Siri-as-a-Service Speech API
Yes we plan to release an offline lightweight runtime that allows you to run Wit locally.
wit.ai#speech recognition api#natural language understanding#voice commands#speech to intent
How HN took it
19 positive, 10 neutral or asking, 0 mixed, 2 critical, out of 31 comments about the project. Thread score +0.53.
Idea: 9 for, 0 againstPerformance: 2 for, 0 againstExecution: 0 for, 2 againstDocs: 1 for, 0 againstDesign: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Impressive accuracy for intent understanding without training
From 1 comment
We just did a hack-week project using wit and we were blown away at the accuracy of it. Somehow it figured out 'show me the stories assigned to me' meant our 'find-owned-stories'…
danlash on HN
Exciting for Jarvis-style and home automation use
From 3 comments
Oh my. Cannot wait to give this a shot. I played with Wit awhile back when they launched, and was seriously impressed. This will make it much easier to develop technology for…
endlessvoid94 on HNFAQ seconded. This looks like a potentially amazing product, especially love the potential home automation use cases.
weixiyen on HNMy friends and I did similar thing back in HackMIT. (http://hackmit.challengepost.com/submissions/18093-jarvis) They did most of the work, so kudos to them mostly. If and only if…
yeukhon on HN
Strong demo and platform quality
From 2 comments
Click on, and play for a bit. This is actually a very impressive platform.
swalsh on HNI just tested the html demo tutorial thing. This thing works amazingly.
lcasela on HN
Objections
Sending home or personal speech to servers raises privacy concerns
From 2 comments
Nice demo! But someone has to play devil's advocate, so please allow me: why would I send commands about what I do in my house to your servers? Especially since you apparently…
kleiba on HNAny chance for those of us with lots of spare CPU and memory resources lying around to get ahold of a standalone server package? This out of an interest of all of not relying on…
existencebox on HN
Firefox not supported
From 1 comment
Why do you not support Firefox? WebRTC and WebAudio have hit Firefox stable. Do feature detection, not UA detection.
Sir_Cmpwn on HN
Requests
Offline or self-hosted server version
From 3 comments
Nice demo! But someone has to play devil's advocate, so please allow me: why would I send commands about what I do in my house to your servers? Especially since you apparently…
kleiba on HNI'm very interested in using this for robotics, especially RoboCup. That that latter case, I can't use an internet connection, the robot must be fully autonomous and independent.…
ragebol on HNAny chance for those of us with lots of spare CPU and memory resources lying around to get ahold of a standalone server package? This out of an interest of all of not relying on…
existencebox on HN
FAQ covering accuracy, audio length and accents
From 2 comments
Nice - does this work for unconstrained speech - as in would this work for use-cases like transcription? What's the maximum audio length supported? Is accent an issue?…
balakk on HNFAQ seconded. This looks like a potentially amazing product, especially love the potential home automation use cases.
weixiyen on HN
Date parsing examples and entity docs
From 1 comment
Off topic but a question regarding text to intent object parsing: Is there any date entity in the wit directory? How do I parse a date for e.g. 17th Feb or feb 27 or 13/02?…
x3c on HN
Questions
What NLP and speech engines are used behind the scenes
From 2 comments
This is the first startup in the last 6 months that has me genuinely excited. Congrats! I know this is considered bad mannered, but what's the NLP behind the scenes look like?…
forgotprevpass on HNWhich speech recognition engine do you use? Kaldi? Sphinx? Good ol' HTK? Homemade? With deep learning acoustic models?
snippyhollow on HN
Whether speech samples are used for training
From 1 comment
Does Wit also use the fragments of speech that get sent over the API as a dataset for training Sphinx?
ragebol on HN
Who is behind the project
From 1 comment
All cool, but who is behind this project?
nighthawk24 on HN
Alternatives named
Google Web Speech API
From 1 comment
This is pretty cool! Google's Web Speech API can also be used to build something similar. Here is the Web Speech API Demonstration:…
jahansafd on HN
Maluuba
From 1 comment
http://www.maluuba.com Does the same as wit.ai I guess
jamesfranco on HN
Ask Ziggy
From 1 comment
I contacted them a while ago and they stated that they will let developers create their own intents soon. http://www.ask-ziggy.com is also similar
jamesfranco on HN
CMU Sphinx
From 1 comment
Here is a link of an open source project. http://cmusphinx.sourceforge.net/ Looks like they are using it for their project…
imtu80 on HN