Discover how to Cost Effectively Plan
Scale your Speech-enabled Applications
Sizing LumenVox Deployments
In general, the number of simultaneous speech sessions that can be reliably run varies with the capacity of the machine and the type of speech recognition being performed. For instance, recognizing a single digit is computationally less “expensive” than recognizing a full street address from a complex grammar.
When building speech applications we’re often asked, “How many ports or channels can I run on a given machine?”
It’s not simply the number of words present within a grammar, but is also how the grammar rules are structured. Rules that have variable phrases, or recursion for example, are more computationally complex than rules containing simply one or two words.
Main Contributors to the Amount of CPU and Memory Resources Needed by a Speech Application
We factor a number of different things including the complexity of grammars used, the number of concurrent calls, the ratio of speech recognition to DTMF processing within an application, the average call duration, and the average number of ASR operations within a call.
All of these factors affect the overall sizing calculation, so it is virtually impossible to be completely certain of a maximum number of channels a given system can run without actually performing some tests using the actual application and measuring system memory and CPU use under load.
LumenVox Sizing Tools
Guidance and sizing estimates for certain machine specifications are available upon request. However, we always recommend performing some testing against the production application to get actual performance metrics.
Distributed and High-Availability Architecture
It is also important to remember that the LumenVox product architecture is designed for modular scalability and redundancy.
Also, LumenVox is continuously developing new methods to enable greater scale and efficiency, so be sure to review the latest versions of LumenVox products when sizing a new application.