Infovista Announces sQLEARas World’s First Machine Learning-Based Standard for 5G VoNR Voice Quality Testing Approved by ITU

The sQLEAR algorithm takes network parameters and standardized voice codec and client information and uses machine learning to provide mobile operators with the network-centric, device-agnostic, audio path-independent, real-time view of the true voice quality being delivered through their 4G and 5G networks. This significantly reduces both cost and time to market of new 5G voice services, while cost-efficiently maintaining high quality standards for existing VoLTE services.

Top iTechnology Networking News: PROS Acquires Digital Offer Marketing Pioneer EveryMundo

Free of devices’ audio path impact, sQLEAR empowers operators with cost-effective, network-centric monitoring, optimization, troubleshooting and benchmarking of their 4G and/or 5G networks, without the need to individually test all commercial devices. The approved ITU-T P.565.1 algorithm exploits ML capabilities to describe the impact on voice quality of the increasingly complex network, voice codec and client interdependencies that are inherent in the all-IP voice networks (VoLTE, VoNR). This enables operators to save time and money, both by optimizing their networks for all, rather than for specific, devices and by being able to quickly identify any network-based issues without the interference from device characteristics which could mislead root cause analysis.

“Launching new voice services over 5G New Radio (VoNR), while maintaining the voice service quality and growing voice revenue through VoLTE expansion with minimized CAPEX/OPEX, is one of today’s key concerns for mobile network operators,” said Dr. Irina Cotanis, technology director of network testing at Infovista. “With the GSA now reporting over 1,100 5G announced devices globally, it is no longer practical or financially viable to test every individual device for its voice quality. Furthermore, mobile all-IP-based voice as well as the 5G New Radio bring new complexities and interdependencies that require a fundamentally new approach to make voice testing effective and efficient. This is what drove us to re-think the QoE modelling concept, which we introduced as study item to ITU-T Study Group 12. After several years working with ITU, we are delighted that the sQLEAR ML-based algorithm has been validated and approved as standard – reflecting the importance of AI/ML for QoE/QoS modelling.”

sQLEAR is the first step in a broader Infovista strategy of developing ML/AI-based network-centric quality of experience testing, including OTT voice apps today and eGaming and other experience-rich IP-based 5G services in the future.