GlossarySynthetic Speech Detection
What is Synthetic Speech Detection?
In short
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).
Mentioned in
- The Hidden Cost of Agentic AI CallersArticle
- Cheapfakes Not Deepfakes: The Real Threat to Your Contact CentreArticle
- Silicon Valley Misses the Call Centre Reality of Voice BiometricsArticle
- Voice Biometrics Partner Selection and MigrationArticle
- What is Microsoft's Voice Biometrics Endgame?Article
- Is Apple's new Personal Voice and Live Speech a security risk?Article
- What are the latest deepfake speech tools?Article
- Is the latest attack on Synthetic Speech Detection 99% effective?Article
- More data breaches, the darknet economy and generative AIArticle
- Battling Deepfakes and Synthetic Voices in Voice BiometricsVideo