VoiceTone -- version 2.0

Beijing Kexin Technology Limited

Introduction :

Our VoiceTone is a such an engine that it combines our embedded recognition engine (MSR) and MTTS together, designed specifically for high end cell phones (such as PDA phone and smartphone), providing an easy way to operate mobile device via SR commanding. User just say a wanted name, our VoiceTone will show the relative information about the wanted, and dial the wanted's number at a voice hint.

Our VoiceTone works on embedded OS with very limited resource, such as Windows CE or equivalent OS, it can complete recognition, commanding and other tasks under very limited resource. The VoiceTone is purposely designed for interface on embedded systems, it makes the operation of mobile systems even more humanized, especially makes those aged and disabled people easily and conveniently use mobile devices.

Features :

  Based on speaker independent HMM technology

  No enroll or training process is necessary

  Seamless integrated with MS Pocket Outlook contact list

  Realize hands-free and eyes-free dialogue usage model

  Not sensitive to accent, can recognize Chinese names, common English names, and Chinese-English mixed names

  Dynamic pronounce creation (via text label and/or speech label) for uncommon words

  Pre-defined global system command make PDA/phone control more simple (user can define more if wanted)

Technical parameters ( VoiceTone 2.0 ) :

Running environment

  Intel StrongARM/Xscale serial CPU

  Microsoft Windows for Pocket PC 2002 (Phone Edition) Chinese Version

At least 500KB storage memory for installation, and 2MB memory for program running

Need speech input device, e.g. microphone

  Performance

  Under normal usage condition, when the distance between lip and microphone is about 20-40cm, speech recognition accuracy is above 95%

  With name number increasing, the resource increasing is very less

  Real time response speed with imperceptible delay