CallMiner has announced a major upgrade of its CallMiner Eureka system. The company says its flagship platform, which is designed to automatically transcribe speech, is now somewhere between 80 and 90 percent accurate in recognizing words, can perform ten times faster than real-time, and is compatible with more than 20 languages and dialects.
The upgrade will be delivered in version 10 of the engine, which CallMiner aims to launch this month. It’s a further refinement of the speech recognition system, which received a powerful technological infusion last year when it integrated SpeechPro technology allowing it to differentiate between the speakers on a call.
For CallMiner, the upgrade could prove critical as the company’s technology is increasingly rivalled by offerings from giants such as Amazon and Google, companies that are in an intensifying arms race in the field of speech recognition as voice-based user interfaces prove increasingly important.
In a statement, CallMiner CEO Terry Leahy explained that “[i]mprovements in accuracy as well as speed-to-intelligence can have an immense impact on our customers’ ability to rapidly respond to a consumer’s question or address an issue,” adding that “the capability to support more languages and dialects will allow us to better support our global customers and partners and expand into other regions of the world.”
July 11, 2016 – by Alex Perala