Manolis Perakakis world

News, diary, journal, whatever

Prime time for Distributed Speech Recognition? February 23, 2009

While an undergraduate student a few years ago I worked on Distributed Speech Recognition (DSR). The main purpose of DSR is to compress the acoustic features used by a speech recognizer, over a data (instead of voice) network, thus saving bandwidth (cost effective) and allowing the use of full speech recognition in mobile terminals. As it compresses acoustic features for speech recognition (not speech signal transmission/reproduction) purposes it can achieve very low bit rates. You can think of it as analogous of what mp3 is for music transmission and storage.

Depicted next is a simple overview of a DSR architecture (model 2). Note that the mobile terminals depicted are Symbian’s reference devices corresponding to smartphone, handheld and PDA respectively (Ooops too old images – it should be back in 2001; should upgrade to something like iPhone or Android …)

My work with Prof. V.Digalakis concluded that one can successfully take advantage of DSR with only a 2 kbps coding, which is an extremely low data rate. After that i ported the DSR engine to a Zaurus Linux PDA and made it work in real-time (a 16MB, 200 MHz StrongArm processor).

Although my recent work focus is now on Multi-modal (speech) interfaces I still keep an eye on DSR. It seems that with the emergence of powerful mobile terminals and the announcement of speech recognition support for Android and iPhone by Google, DSR might become soon a hot topic!

P.S. I just found out my DSR page is ranked 3rd by Google after W3C and ETSI. Holy moly!

Coolness factor: ?

 

Nokia buys Trolltech, gets on the mobile Linux bandwagon! January 28, 2008

Filed under: embedded,Linux,mobile,technology — perak @ 8:39 pm

I just came across this linuxdevice article, according to which Nokia will buy Trolltech! Interesting news! It seems Nokia is willing to adopt Linux in mobiles, in addition to the already Linux based web-pads (N800, N810) which use the Maemo environment (based on Gtk+/gnome). Expect a Gtk+/Qt war in the mobile platform arena too!

Nokia had already made a move towards Linux by embracing the “Open C” libraries last spring in order to help accelerate application development and porting to the Symbian OS.

After the recent Linux push by Google Android, it seems everybody is rushing to get on the mobile Linux bandwagon! Until now, only Motorola tried to embrance Linux, with limited success in far east Asia (China mainly).  The Nokia move will hopefully have a great effect on Linux penetration. With this move Nokia will finally lead two different mobile OSes (Symbian and Linux) which is a very cool move against the rest players (see Microsoft!)

 

Trolltech releases Qt Jambi! July 28, 2006

Filed under: C++,embedded,GUI,Java,programming — perak @ 11:31 pm

Trolltech just released Qt Jambi, a java library for the desktop version of QT. Development with QT & QTopia (QtEmbedded) had been a really exciting experience for me in the past (well that was 2002; with my QtJim QTopia jabber client). It was a cool paradigm shift away from Swing’s mess of that time.

Sometime in 2005 i ported Qtjim to SWT in just a day! I found SWT to be also extremely nice as an API. And yes, i am still waiting for those SWT bindings for Qt/Qtopia (SWT uses Gtk bindings). Some people also proposed that IBM buys Trolltech, so it seems Jambi was a way for Trolltech to fight back!

Now, i think it’s really nice to use the power of Qt directly from Java. I recall how painful, the porting of an AWT application to Zaurus was : I had to fight different QT bindings for CVM/J9 and the worse part is, i could not use the OpenZaurus ROM (had to stick with Sharp’s original or TheKompany’s ROM).

But will Jambi be a success or just add fragmentation?
Well, time will tell

pros :

  • exposes excellent QT, to java programmers (java on desktop might get finally real )
  • eliminates jvm-vendor QT-bindings lock-in

cons :

  • Only for J2SE 5!! (the real usefulness would be for the embedded space, trolltech folks! – hope they make it for embedded too!)

coolness factor : 4.25!