(OCT 2006) — The LumenVox Speech Tuner has undergone a major rewrite, and the new version is now available for download as a beta release.
It is now much faster at loading data and a revamped GUI makes it easier to use.
New shortcut keys and auto–text speeds up transcription by several times, cutting your tuning time significantly. While transcribers are entering information, the Transcriber will automatically fill–in transcription from the Speech Engine, which means in many cases an entire utterance can be transcribed with one button press.
The entire Tuner has been designed with speed in mind: loading call databases is much quicker, and users can apply filters to call and interaction data before loading all of the call details in order to save even more time.
Other improvements include:
Transcripts entered with the Transcriber tool are helpful to tuning a speech application. They are used to perform tests on a speech application in order to pinpoint problems.
While transcribing, you should be mainly concerned with audio that is appropriate for the speech application and that is recognizable by humans. It is a subjective process and transcribers should strive to maximize their efficiency.
For instance, if the application records a caller talking to another person in the background, that speech can simply be marked as garbage and discarded while doing tests. Likewise, if a caller says something that is unintelligible to a human, there is no way the Engine can be expected to understand it and thus it can be marked as garbage as well.
What should be transcribed are utterances that are appropriate for the application. This includes intelligible out–of–grammar responses when those responses make sense as being valid responses to the prompt.
If you would like to participate in the Speech Tuner beta test, contact us for more information.
A new interface is more than just eye candy: it is now simple to use the Call Browser in order to see exactly how a call progressed and improved statistics and information throughout the Speech Tuner provide greater clarity.
Screenshots of the new Tuner and a lot more information about it are available at the new LumenVox Tuner Web site.
The Speech Tuner will run on most modern Windows systems. We recommend at least 512 MB of system memory, and large batch tests may require 1 to 2 GB.
The Speech Engine requires an 800MHz or greater processor with 1 GB of RAM. It will run on modern versions of Windows (NT4, 2000 and up) as well as certain distributions of Linux.
The Tuner can be used with data from Speech Engines running on either Windows or Linux. If you have any questions about running the Tuner on your systems, please contact us.
Finally, a fully–integrated speech solution for all Asterisk–based applications is now available.
In conjunction with Lumenvox, Digium, the company behind the Asterisk PBX, has integrated the LumenVox Speech Engine directly and seamlessly with the Asterisk platform and Dialplan scripting through a unique connector bridge that Digium created.
Now you can easily build speech–enabled IVRs by using the familiar Dial Plan scripting language or the C–API.
Supported Linux distributions include: rPath™ Linux (Digium), and Red Hat Enterprise Server 4.
© 2016 LumenVox, LLC. All rights reserved.