Voice security startup Pindrop launches Deep Voice 3, a voice recognition engine built on machine learning and deep neural networks

Pindrop, a voice security and authentication startup, 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.  Pindrop claimed the new updated voice recognition engine improves authentication rate by 30%, enhancing customer experience and call center efficiency.

Pindrop was founded in 2011 by Dr. Mustaque Ahamad, Paul Judge, and Vijay Balasubramaniyan. Pindrop solutions protect some of the biggest banks, insurers, and retailers in the world using patented technology that extracts an unrivaled amount of intelligence from every call encountered. Pindrop solutions help detect fraudsters and authenticate callers, reducing fraud and operational costs, while improving customer experience and protecting brand reputation.

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’).

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.

“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.

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.