Automatic Speech Recognition (ASR)
LumenVox ASR Technical Summary
The hardware resources required by the LumenVox Automatic Speech Recognition (ASR) engine vary significantly depending on the exact task being performed. The main variables involve the length of audio, total number of simultaneous channels of recognition, and the type of application (specifically the size and complexity of the grammars being used).
For production telephony systems, LumenVox recommends a minimum configuration of a modern server running a 64-bit operating system with 4 CPU cores and 8GB of RAM.
Supported Operating Systems
2012*, 2016*, 2019* Server (32 & 64-bit)
Windows 10 (32 & 64-bit)
*Windows Server 2012, 2016 and 2019 requires a 64-bit processor, however it can run both 32 & 64-bit applications.
Red Hat & CentOS 7 (32 & 64-bit)
VXML (Voice XML)
SRGS (Speech Recognition Grammar Specification)
GrXML (Grammar XML, an SRGS format)
SISR (Semantic Interpretation for Speech Recognition)
C/C++ API (Application Programming Interface)
MRCPv1, MRCPv2 (Media Resource Control Protocol)