Updated Voice Recognition Engine Improves Authentication Rate by 30%, Enhancing Customer Experience and Call Center Efficiency
Pindrop, the pioneer in voice security and authentication, announced the launch of Deep Voice 3, the new version of its market-leading voice recognition technology. Built on advanced machine learning and deep neural networks, Deep Voice 3 is designed to more accurately recognize the voice of callers at a contact center with less speech. This allows: (1) end-users to be authenticated more quickly, (2) higher enrollment rates enabling a smoother customer experience and (3) a more efficient, secure contact center.
“Our 2020 Voice Intelligence and Security Report shows that fraudsters are getting more sophisticated, focusing their energy on channels where they can get the biggest payday; in other words, fewer, bigger attacks”
Deep Voice 3’s technical advances are based on the continuous innovation taking place at Pindrop. Building on its deep industry experience, Pindrop was able to combine a rearchitected neural network and an advanced training program to teach the system based on real-world learnings. This led to the development of the new version, with its advances in accuracy and speed.
Deep Voice 3 opens the door for strong authentication with brief snippets of speech. This enables numerous use cases especially in IVR and IoT applications where speech is conveyed in the form of small commands. Specifically, in IoT this enables speaker identification in as little as three syllables allowing for personalization on utterances as short as wake words (for example; ‘OK Google,’ ‘Hi Bixby,’ and ‘Alexa’).
Recommended AI News: ABB Joins Global Syndicate to Invest in Spear Power Systems
Deep Voice 3 has been optimized to perform across a variety of acoustic and noise environments. Adapting to session variability improves authentication accuracy when handling differences in background noise conditions that exist between a caller’s enrollment and authentication calls. Pindrop has been analyzing the impact of Deep Voice 3 across a number of strategic customers who are already utilizing the Pindrop® Passport authentication solution, and many of these partners expect to see a 30% improvement on their authentication and enrollment rates.
The technology will be unveiled at the RSA Conference, taking place at the Moscone Center in San Francisco, CA on February 24-28. Pindrop will be exhibiting at booth N-5670.
“In today’s contact center, companies are working to deliver the kind of seamless customer experience that consumers get everywhere in their digital life. This means confidently authenticating more callers, and doing so at a significantly faster rate,” said Vijay Balasubramaniyan, CEO of Pindrop. “Deep Voice 3 is a crucial part of the technology that is making that possible, and taking us a step closer to frictionless identity in a voice-first world.”
Deep Voice 3 will be generally available this quarter to new customers, via the Pindrop® Passport authentication product. In the coming months, Deep Voice 3 will be incorporated into Pindrop’s anti-fraud Protect product. Pindrop’s customer base includes eight of the top 10 banks in the U.S., as well as five of the top seven insurance companies.
Recommended AI News: Hyperledger Fabric 2.0 Arrives to Boost Enterprise Blockchain Adoption
Updated Voice Intelligence and Security Report
Also today, Pindrop released the latest version of its Voice Intelligence and Security Report, the industry-leading report on voice fraud and authentication. The report shows that in 2019, one out of every 770 calls to contact centers was fraudulent – a rate of 90 per minute.
Key findings from the report include:
- 90 voice fraud attacks occurred per minute in 2019
- Overall voice fraud remained near its 2018 peak of one call in every 685 being fraudulent across the surveyed industries
- The banking industry saw a 15% increase in phone fraud when compared with 2018. This is particularly notable as banking remains the single largest channel for contact center calls.
“Our 2020 Voice Intelligence and Security Report shows that fraudsters are getting more sophisticated, focusing their energy on channels where they can get the biggest payday; in other words, fewer, bigger attacks,” Balasubramaniyan said. “It’s natural that fraudsters would target banks above other industries: there are more calls to banks, and the potential reward of a hacked account is greatest. In 2020, any bank that isn’t thinking about voice security is putting itself and its customers at risk.”
Recommended AI News: Rockset Gains Momentum as the Industry’s Leading Real-Time Database in the Cloud