2
AUTOMATED SPEECH RECOGNIZER LumenVox’s unique solution offers even more efficient support for large speech recognition grammars through advanced server and client-side grammar caching. Server-side speech grammars allow large grammars to be compiled once and saved so that they can be loaded again very quickly and without using up valuable processor or memory resources. SERVER-SIDE SPEECH GRAMMARS - efficient support for large speech grammars and compiled grammars Our adoption of standardized protocols and development tools make it easy to replace your existing ASR with the LumenVox solution. Our Media Server supports MRCP v1 and 2, we are VXML and PCI compliant, and our grammars can be written in GrXML or ABNF, with SISR and SRGS capabilities. STANDARDS SUPPORT - let industry standards simplify development DISTRIBUTED CLIENT/SERVER ARCHITECTURE - seamlessly grow your speech environment DEVELOP INNOVATIVE AND DYNAMIC SPEECH-ENABLED SOLUTIONS You can’t afford service outages or hardware failures. The versatility of the LumenVox client/server architecture allows your administrators to seamlessly grow speech environments. This distributed architecture provides stability through redundant installations and achieves higher levels of performance through load balancing, without requiring increased processor load. Build World-Class Speech Applications www.LumenVox.com Key Benefits of LumenVox ASR Whether the call is coming from a crowded restaurant or inside of a speeding car, the LumenVox Speech Recognizer separates speech from background noise using Voice Activity Detection (VAD). VAD listens for energy level (volume), frequency (pitch), changes in frequency and duration qualities to accurately detect the actual speech. ACCURATELY DETECT SPEECH IMPROVE USER EXPERIENCE FLEXIBLE PRICING With a selection of licensing options to choose from, it is easier than ever to deploy LumenVox’s suite of products. Options include per-port, monthly subscription, use- based, bursting, and Software as a Service (SaaS). In most cases, the LumenVox software will be deployed locally to your application, right where you want it for optimal results. Using NBest, the system can prompt the caller with the best results, ultimately eliminating the need for the caller to continuously repeat themselves. This is is particularly effective when callers need to spell names, street addresses or email addresses. The LumenVox Automated Speech Recognizer (ASR) is a software solution that converts spoken audio into text. Not all ASRs provide the same capabilities and some may be limiting and constraining. The LumenVox ASR is an industry leader in its ability to recognize naturally spoken language and its tuning flexibility, which provides for quality user experiences and high user completion rates.

AUTOMATED SPEECH RECOGNIZER · turned into a waveform, a mathematical representation of sound. The engine looks at features — distinct characteristics of sound — derived from

  • Upload
    others

  • View
    2

  • Download
    0

Embed Size (px)

Citation preview

Page 1: AUTOMATED SPEECH RECOGNIZER · turned into a waveform, a mathematical representation of sound. The engine looks at features — distinct characteristics of sound — derived from

AUTOMATEDSPEECH RECOGNIZER

LumenVox’s unique solution offers even more efficient support for large speech recognition grammars through advanced server and client-side grammar caching. Server-side speech grammars allow large grammars to be compiled once and saved so that they can be loaded again very quickly and without using up valuable processor or memory resources.

SERVER-SIDE SPEECH GRAMMARS - efficient support for large speech grammars and compiled grammars

Our adoption of standardized protocols and development tools make it easy to replace your existing ASR with the LumenVox solution. Our Media Server supports MRCP v1 and 2, we are VXML and PCI compliant, and our grammars can be written in GrXML or ABNF, with SISR and SRGS capabilities.

STANDARDS SUPPORT - let industry standards simplify development

DISTRIBUTED CLIENT/SERVER ARCHITECTURE - seamlessly grow your speech environment

DEVELOP INNOVATIVE AND DYNAMICSPEECH-ENABLED SOLUTIONS

You can’t afford service outages or hardware failures. The versatility of the LumenVox client/server architecture allows your administrators to seamlessly grow speech environments. This distributed architecture provides stability through redundant installations and achieves higher levels of performance through load balancing, without requiring increased processor load.

Build World-Class Speech Applications

www.LumenVox.com

Key Benefits of LumenVox ASR

Whether the call is coming from a crowded restaurant or inside of a speeding car, the LumenVox Speech Recognizer separates speech from background noise using Voice Activity Detection (VAD). VAD listens for energy level (volume), frequency (pitch), changes in frequency and duration qualities to accurately detect the actual speech.

ACCURATELY DETECT SPEECH

IMPROVE USER EXPERIENCE

FLEXIBLE PRICINGWith a selection of licensing options to choose from, it is easier than ever to deploy LumenVox’s suite of products. Options include per-port, monthly subscription, use-based, bursting, and Software as a Service (SaaS). In most cases, the LumenVox software will be deployed locally to your application, right where you want it for optimal results.

Using NBest, the system can prompt the caller with the best results, ultimately eliminating the need for the caller to continuously repeat themselves. This is is particularly effective when callers need to spell names, street addresses or email addresses.

The LumenVox Automated Speech Recognizer (ASR) is a software solution that converts spoken audio into text. Not all ASRs provide the same capabilities and some may be limiting and constraining. The LumenVox ASR is an industry leader in its ability to recognize naturally spoken language and its tuning flexibility, which provides for quality user experiences and high user completion rates.

Page 2: AUTOMATED SPEECH RECOGNIZER · turned into a waveform, a mathematical representation of sound. The engine looks at features — distinct characteristics of sound — derived from

LumenVox and the LumenVox logo are either trademarks or

registered trademarks of The LumenVox Corporation and are

registered in the United States. All other trademarks are the

property of their respective owners. © 2019 The LumenVox

Corporation. All Rights Reserved.

03-19A

WANT TO LEARN MORE?

WWW.LUMENVOX.COM

US: 591 Camino De La Reina,

Suite 1040, San Diego, CA 92108

EU: Hofmannstr. 25-27

D-81379, Munich, Germany

[email protected]

EMAILUS: +1 858 - 707 - 7700

JUST SAY “SALES”

EU: +49 (89) 127 16 0

PHONE

LEARN MORE ABOUT LUMENVOX AUTOMATED SPEECH RECOGNIZER.CONTACT US TODAY!

HOW SPEECH RECOGNITION WORKS The engine loads a list of words to be recognized. This list of words is called a grammar.

Speech recognition presents an exciting and dynamic set of opportunities for creating great user experiences and efficiencies. Speech applications today range from self-service telephone applications such as banking applications, to mobile applications that allow users to speak commands and compose messages with their voice. In the future, we can expect to see virtually every sort of application integrate speech recognition in some form.

LumenVox technology is the foundation of a successful speech solution.

We provide the tools to help you communicate more effectively, increase efficiency, reduce operating costs, increase customer satisfaction and improve employee productivity.

LumenVox is well known for our outstanding customer service as we guide you through your speech application development and deployment process. And we’re there for you with joint sales, marketing, education, training and customer support teams and programs after you’ve deployed your speech solution.

GET TO KNOW

Audio from a speaker is captured by a microphone or telephone. This audio is turned into a waveform, a mathematical representation of sound.

The engine looks at features — distinct characteristics of sound — derived from the waveform and compares them with its own acoustic model.

The engine searches its acoustic space, using the grammar to guide this search. It then determines which words in the grammar the audio most closely matches and returns a result.