Tag Archives: Project Glass

Useful Links for Voice Recognition

Posted on by

As we have seen more and more applications and devices using voice recognition especially on Android and iOS and because I have been working with applications that use voice recognition I have put together some links that maybe useful for applications using voice recognition. I have used several of these for applications including the project glass inspired work.

µSpeech (muSpeech)

This library is for arduino and provides an interface for voice recognition using the Arduino, which does voice recognition in a way different from most high powered voice recognition methods. It calculates the complexity of the signal is determined by taking the absolute derivative of the signal multiplying it by a fixed point saclar and then dividing it by the absolute integral of the signal. This project is hosted on github so go take a look.
http://arjo129.github.com/uSpeech/

Dragon Naturally Speaking

Developed by Nuance this is one of the most advanced voice recognition offerings out there. The SDKs are available for client use or as a server side service.
http://www.nuance.co.uk/for-developers/dragon/index.htm

Microsoft Speech API

Offered by microsoft and integrated into kinect for windows parts (tutorial here), it provides voice recognition of a word or phrase from a set list.
http://msdn.microsoft.com/en-us/library/dd266409.aspx

AT&T Watson Speech Recognition

This offering by AT&T provides full voice recognition from a cloud based offering but uses advanced category indication to help Watson identify what you are saying. ie you can tell it if the category is business and it refines it’s recognition.
http://www.research.att.com/projects/WATSON/index.html?fbid=_wsE6gQcLDc

iSpeech

Part of one of the most successful apps on android, iOS and Playbook iSpeech provides a Text to Speech cloud service that is easy to use and integrate. They offer mobile SDKs to get you up and running quickly.
http://www.ispeech.org/

SpeechFX

This recognition SDK performs continuous recognition giving you full voice trasncoding.
http://www.speechfxinc.com/voicein.html

Voxler

Provides speech recognition for 25 major languages.
http://www.voxler.fr/index.php/what-we-do/speech-recognition-sdk

Sphynx Voice Recognition

This is a good open source voice recognition solution.
http://cmusphinx.sourceforge.net/

 

Bookmark and Share

Project Glass: Real Time Translation … inspired

Posted on by

I have created a new project glass inspired video which works on translating realtime conversations and displaying it as subtitles in your glasses. I can have a conversation with Elizabeth who speaks Spanish to me and I return with English. I have never learnt Spanish but using the glasses I can have a full conversation. To make this possible I used:

  • 2x Raspberry Pi running debian squeeze
  • Vuzix 1200 Star
  • Jawbone Mic
  • Headset Mic
  • TV
  • iPhone
  • iPad
  • Transformer

Follow after the break to find out how it was all put together. Continue reading “Project Glass: Real Time Translation … inspired” »

Bookmark and Share

Project Glass: One Day … inspired

Posted on by

I really like the project glass by Google. To that extent I have created a version using a pair of Vuzix Glasses, Microsoft HD Webcams, mic headset and dragon naturally speaking. Using these combined pieces of hardware I was able to get the head mounted display and voice recognition. I built the application using Adobe Air. The application sports full voice recognition and has the same interface that Google project glass has. The Vuzix glasses are driven by stereoscopic feeds, which are fed by the HD cameras.

Bookmark and Share

CEO Vision – Kinect + Augmented Reality + SAP HANA

Posted on by

I have been the lead developer on CEO Vision. It combines the Microsoft Kinect, Augmented Reality with the SAP HANA. Check out the website to see more about the technology (Click here to visit microsite)

This video stars Nic Doodson and myself. We demo the object recognition, face tracking and face recognition along with the Microsoft Kinect to allow users to literally reach out and touch their HANA powered reality.

Bookmark and Share