Radisys Unveils New Advanced Speech Recognition Support for Enhanced In-Call Speech Services


Radisys’ Media Server solution reduces cost of deploying speech-enabled services by more than 90%; Allows CSPs to capitalize on mass market acceptance of person-to-application interaction via speech

HILLSBORO, OR, U.S. – February 25, 2019Radisys® Corporation, a global leader of open telecom solutions, today announced new features for its Media Server virtualized media server to enable advanced in-call services, allowing Communication Service Providers (CSPs) to implement speech recognition interfaces at dramatically lower costs than previous solutions. These new features allow CSPs to accelerate new speech-driven service introductions by utilizing off-the-shelf Intel® Architecture servers, advanced media processing with Media Server, and a combination of advanced speech processing engines, to significantly lower OpEx and CapEx, all within a well-defined open API framework.

News Highlights

  • Speech-enabled interfaces have become preferred user interfaces on phones, smart speakers, and home IoT devices. As a result, users now expect speech support for a growing variety of applications including in-call personal assistants, contact center communications, automated bot interactions and more. However, “in-call” speech recognition solutions to date have been primarily limited to call centers as a replacement for IVR (touch tone) applications. Cloud-based solutions that support in-call speech enablement require extensive and costly hardware, and one-size-fits-all natural language speech recognition engines, making scalable deployment of network-based speech-enabled applications expensive for high-volume applications.
  • Radisys’ Media Server offers new features that enable CSPs to overcome the challenges associated with the traditional in-call speech-enabled applications, and deploy innovative new solutions, including enhanced customer service or application navigation (like in-conference commands for more hands-free capability), or to develop new revenue streams by using speech analytics to build actionable customer engagements. These new features include:
    • Embedded in media server key word detection delivers a small footprint key word or key phrase speech recognition engine, allowing for an “always on” solution that reduces costs of deploying speech enabled services by over 90%.
    • Integrated support for multi-vendor best-in-class server based in-network or cloud speech platforms for advanced speech interactions including natural language conversational recognition, and text-to-speech processing, allowing service providers to pick the best technology for their particular use case. 
    • Voice Quality Enhancements (VQE) to overcome telecom network or environmental conditions that can reduce in-call recognition accuracy.
  • Radisys’ Media Server software with embedded real-time advanced speech processing and media analytics allows CSPs to create, deliver and monetize new applications by delivering cost-effective advanced technologies that were previously cost prohibitive for many innovative applications.

“As speech technology has evolved, there are a growing number of opportunities for service providers to develop network-based speech-enabled applications that will drive new revenues,” said Sue Rudd, Director of Networks and Service Platforms, at Strategy Analytics. “Radisys has added some very innovative features that will allow service providers to introduce a range of cost effective, scalable, hosted solutions from conference call add-ons, to call center services and analytics and even IoT triggered voice. This approach enables service providers to add significant value with mass market ‘in-call’ speech recognition services at significantly lower cost.”

“With the continued drive toward more speech-enabled devices and services, CSPs are well positioned to address the gap in in-call speech solutions,” said Al Balasco, vice president, MediaEngine, Radisys. “Radisys’ Media Server’s integrated speech recognition capabilities enable service providers to overcome the cost, complexity and quality challenges associated with traditional in-call speech-enabled services, while adding complementary media processing features for advanced applications and services using open APIs.”

Meet with Radisys at MWC 2019

Radisys will showcase Media Server’s in-network real time in-call speech recognition and media analytic innovations in its booth in Hall 5, Stand 5I61 during Mobile World Congress, February 25-28 in Barcelona. To see the technology demonstrations, or to meet with Radisys’ media processing experts to learn more, contact open@radisys.com.  


About Radisys

Radisys, a global leader in open telecom solutions, enables service providers to drive disruption with new open architecture business models. Radisys’ innovative disaggregated and virtualized enabling technology solutions leverage open reference architectures and standards, combined with open software and hardware to power business transformation for the telecom industry, while its world-class services organization delivers systems integration expertise necessary to solve communications’ and content providers’ complex deployment challenges. For more information, visit www.Radisys.com.


Radisys® is a registered trademark of Radisys. All other trademarks are the property of their respective owners.




Previous Flipbook
Media Server Datasheet
Media Server Datasheet

Software-based Media Processing Solution with Industry-leading Performance and Scalability for Public and P...

Next Article
“Hey Siri…” – How Radisys is Advancing the Growth of Speech-Enabled Applications and Services
“Hey Siri…” – How Radisys is Advancing the Growth of Speech-Enabled Applications and Services