Is voice biometrics used only for live-agent interactions or does it work with intelligent virtual agents too?
Voice biometrics can provide authentication for interactions that take place with humans as well as with intelligent virtual agents (IVAs). Voice biometrics and IVAs are complementary solutions that deliver enhanced and additional benefits when used in conjunction with each other. Voice biometrics solutions use unique characteristics of a voice – such as cadence, accent, pitch and tone – to identify the speaker. Voice biometrics technologies operate in two primary ways: active solutions depend on the use of certain words or phrases in order to authenticate, and passive applications identify speakers during the normal flow of conversation. Both types of voice biometrics establish a baseline, or enrolled voiceprint, then compare future conversations against the initial sample. Subsequent conversations that match the enrolled voiceprint allow speakers to be authenticated in the application, and conversations that don’t match the enrolled voiceprint help companies identify and avoid potentially fraudulent interactions.
Voice biometrics can shorten interaction handling times by performing authentication in the background of a live agent call, reducing or eliminating other time-consuming forms of caller verification. When used with IVAs, voice biometrics solutions enable enterprises to expand use cases to include activities that can be completed only post-authentication. IVAs that utilize voice biometrics can also alert administrators when attempts are made to complete a fraudulent transaction via self-service that a fraudster might not try to pull off with a live agent. Additionally, voice biometrics can be used with internal-facing IVAs to authenticate employees for self-service activities such as call-outs or clock-in/clock-out transactions.