Redesigning the Voice Relevance Engine for Scale and Reliability (2022)

By Eileen Bengston, Ferhan Ture; Comcast

At SCTE in 2012, a group from Comcast presented the Voice Relevance Engine for Xfinity (VREX). Its goal was to understand human utterances for video search and discovery and to take an appropriate action. Since then, Comcast’s voice system expanded to cover numerous platforms, won a technical Emmy, and was used for more than 10 billion voice commands last year alone. After running at scale for 10 years, the voice system is being redesigned to suit the new and growing demands for voice control across a range of products.

The original system as described at SCTE in 2012 [1] was divided into three major areas: automated speech recognition (ASR), natural language processing/natural language understanding (NLP/NLU), and action resolution (AR). These services and the division of labor therein include: first determine what the user said, second understand what the user meant, lastly decide what the system should do to resolve the request.

By clicking the "Download Paper" button, you are agreeing to our terms and conditions.

Similar Papers

V-REX – Voice Relevance Engine For Xfinity
By Stefan Deichmann, Oliver Jojic, Akash Nagle, Scot Zola, Tom Des Jardins, Robert Rubinoff, Amit Bagga, Comcast Labs
Photon Avatars in the Comcast Cosmos: An End-to-End View of Comcast Core, Metro and Access Networks
By Venk Mutalik, Steve Ruppa, Fred Bartholf, Bob Gaydos, Steve Surdam, Amarildo Vieira, Dan Rice; Comcast
Full Scale Deployment of PMA
By Maher Harb, Bryan Santangelo, Dan Rice & Jude Ferreira, Comcast
Two Years Of Deploying ITV/EBIF Applications – Comcast’s Lessons Learned
By Robert Dandrea, Ph.D., Comcast Cable
Why Scale Needs Unity: One Operator’s Journey
By Elizabeth Riley-Wasserman, Ph.D. & Shane Portfolio, Comcast
Voice Control of Set-Top Box for Customers with Non-Standard Speech
By Adina Halter, Comcast; Sara Smolley, Voiceitt
Rapid and Automated Production Scale Activation of Expanded Upstream Bandwidth
By Rob Thompson, Rob Howald, John Chrostowski, Dan Rice, Amarildo Vieira, Rohini Vugumudi & Zhen Lu, Comcast Cable
Key Learnings from Comcast’s Use of Open Source Software in the Access Network
By Louis Donofrio & Qin Zang, Comcast Cable; Vignesh Ramamurthy, Infosys Consulting
Software Reliability Engineering: Scaling the Cloud with Automation
By Brian Gray, Sriram Ramakrishnan & Fei Wan, Sr., Comcast Cable
Running a Multi-Tenant Hybrid Cloud for Large Scale Cable Applications
By Neill A. Kipp, Comcast
More Results >>