By Al Balasco, Vice President, MediaEngine
Automated speech recognition, text-to-speech, and voice recognition will be an $18.3B market by 2023 according to Markets and Markets Speech and Voice Recognition Forecast Report with applications that use speech interfaces growing rapidly across a wide variety of vertical markets. While the ubiquity of speech interfaces is undisputed, there’s one place that the latest speech-enabled services can’t reach – within the context of a live voice or video call. Addressing this gap is of critical importance as it presents a major opportunity for Communications Service Providers to support a wide range of new applications with in-call speech processing and media analytics embedded in their networks, and thereby drive new revenues.
I’m excited to share that our MediaEngine™ Media Analytics solution which integrates Advanced Speech Recognition (ASR) capabilities has won the Pipeline Innovation Award for Analytics. According to Scott St. John, managing editor of Pipeline, “For nearly ten years, the Pipeline Innovation Awards have recognized the technology companies that are transforming the industry with the most significant technical innovations.”
Radisys’ MediaEngine, a virtual media server software, embeds real-time advanced speech processing and media analytics, thereby enabling service providers and system integrators to drive more value for IoT-based services. These new applications create monetization opportunities by delivering cost effective advanced technologies that were previously cost prohibitive for many innovative applications.
MediaEngine provides a unique architecture where the real-time voice media-processing platform is enhanced with embedded speech recognition, voice quality enhancement, and real-time speech analytics capabilities. It offers a flexible framework with Open APIs to optimally leverage the strengths of multiple speech processing solutions and create innovative “in-call” speech recognition applications for mass-market scalable services. One of the key benefits in moving to this architecture is an increase in speech recognition accuracy up to 20% and savings of over 90% in software and CapEx spend.
I recently covered the challenges and opportunities associated with ASR in an article published in Pipeline: Hey Siri, Tell Me About Advanced Speech Recognition.
Bringing Media Analytics to VOICE
Taking place July 22-25 in Newark, New Jersey, the VOICE Summit is the world’s largest event dedicated to voice technologies. Natasha Tamaskar, Radisys’ VP of Global Marketing and Sales Strategy, will present on “Delivering Speech-Enabled Services In-Call: Challenges and Opportunities.”
Please contact us at info@radisys.com if you’d like to schedule a meeting with Radisys during the event.
