Vestec logo
India USA
China Australia
 
main splash image
Robust Affordable Speech Recognition

   • $199 per channel perpetual license
   • Acoustic models for 4 major languages:
   - American English - Chinese Mandarin
   - Australian English - Indian English
   • SRGS (XML & ABNF) grammar format
   • MRCP (v1 & v2) platform integration
   • Scalable architecture & load balancing
   • Asterisk and FreeSWITCH support
   • Linux and Windows installation

Resource Requirements


Vestec ASR utilizes an efficient, scalable client-server architecture that can support thousands of ports given appropriate computational resources. (One “port” refers to one communication “channel”. So, a 4-port setup means simultaneous speech recognition on 4 channels.)

The following table presents sample memory and CPU usage for different number of speech ports (ie. channels) for Tier-1 ASR. The test was conducted on a machine with AMD Athlon II X2 245 dual-core processor, 4GB of RAM, and Linux CentOS 5. The grammar consisted of 500 distinct keywords while the processed audio was 1.6 seconds long. Each test ran for 140 seconds, with each interaction taking an average of 14 seconds.

NUMBER OF PORTSMEMORY USAGE (MB)CPU USAGE (%)
02910
12961
23002
43055
831510
1633427
2436235
3239049
4843876
6448990
NOTE: Memory and CPU usage statistics are machine-dependent.


 
 
 
©2012 Vestec, Inc. All rights reserved.