Researches from Australia came up with a brilliant idea on how to effectively resist a phone scam growing threat. They have developed a conversational AI that wastes the time of phone scammers. It is continuously evolving in response to the fact that scammers constantly change their tactics.
So, what happens when a scammer calls?
- Scammer audio is fed from a server to the Apate chatbot (the solution is described on apate.ai website).
- The bot transcribes this audio in real time into text.
- Then the Apate bot, relying on the cutting-edge conversational AI model, creates a response based on what the scammer said.
- This response is converted into life-like human speech thanks to advanced AI techniques for voice cloning* with emotion modulation.
- The response audio is sent back to the scammer.
As long as a scammer is convinced that the bot is a potential victim, it will keep the conversation that amount to nothing. The model is super clear: More scammers’ time wasted = less time for scamming!
* Voice cloning is a type of “deep fake” consisting of deep learning AI models that generate speech audio that sounds like a given person from text inputs. The person whose voice is being cloned provides recordings of their voice, which are used to train the AI model. Once sufficiently trained, arbitrary text can be provided to the model, and it will “speak” the text in the person’s voice. It is further possible to make variations on the voice to change, e.g., the apparent age and gender of the generated voice and modulate expressed emotion. Numerous publicly available “voice clones” exist, and there are many commercially available voice clones and services in addition (e.g., resemble.ai).