Last updated 2 Jul 2023
Synthetic Speech Detection is a mechanism used to protect Voice Biometrics systems from presentation attacks using synthetic speech. It relies on detecting characteristics inherent in the text-to-speech (TTS) generation process.
Synthetic Speech Detection looks for characteristics of the text-to-speech generation process, such as repetition of identical segments, characteristics of training data sets and security features. This is a probabilistic determination, so at any given threshold, there is inevitably a chance of errors (False Alarms).
Related Terms
Popular Posts
4 mins read
Our Call Centre Security Experience Scorecard gives you the benefit of our 10 years of experience in just 10 minutes. It helps organisations understand how to improve the usability, efficiency and security of their experience.
4 mins read
Nearly all implementations of voice biometrics are driven by promises to make it easier for customers to gain account access, reduce the time spent by front-line agents in authenticating customers, and making sure customers’ personal data and services are secure.
9 mins read
Advances in Speaker Recognition technology and increasing acceptance of conversational interfaces are allowing organisations to authenticate callers using the short utterances now obtained in natural language and speech driven self service applications, without the overhead of traditional active enrolment processes.