top of page

Synthetic speech, how fraudsters use it, how Corsound stops it?

Synthetic speech, or computer-generated speech, is a technology that allows computers to convert written text into spoken language. Synthetic speech systems work by breaking down the text into individual sounds and phonemes and then synthesizing these sounds to produce spoken words.

There are several ways in which synthetic speech can be used, including in automated customer service systems, assistive technology for individuals with disabilities, and educational tools.

However, in addition to the positive things done with this technology, fraudsters can take advantage of it in a variety of ways::

  1. Impersonating someone's voice: By using synthetic speech to mimic someone's voice, a fraudster could potentially impersonate that person and trick call centers into believing they are that person.

  2. Generating automated phone calls: Fraudsters may use synthetic speech to create automated phishing calls that appear to be coming from a legitimate source but are actually designed to trick people into giving away sensitive information or money.

  3. Spreading misinformation: Synthetic speech could potentially be used to create fake audio or video content, such as news reports or political speeches, in an effort to spread misinformation or influence public opinion.

It is important to be aware of the potential risks associated with synthetic speech.

So, what is the best way to prevent fraudsters from using fake audio? Specifically, how can fraudsters be stopped from impersonating you and and stealing your money via the call center?

Corsound Voice biometrics can be used to help prevent fraudsters using synthetic to access customers accounts:

  1. Verifying the voice of the cusomter: By comparing the characteristics of a voice to a stored voiceprint, Corsound voice biometrics systems can help to verify whether a voice is authentic or not. This can help to prevent fraudsters from using synthetic speech to impersonate someone else.

  2. Detecting synthetic speech: Corsound voice biometrics system is specifically designed to detect synthetic speech and distinguish it from real human speech. This system can be used to help prevent fraudsters from using synthetic speech to gain access , get personal information and transfer funds.

  3. Enhancing security measures: Corsound voice biometrics can be used as an additional layer of security in conjunction with other measures, such as passwords or security tokens. This can help to make it more difficult for fraudsters to gain unauthorized access to systems or data, even if they are using synthetic speech.

Call centers can also take additional measures to stop synthetic speech attacks such as training employees to be aware of synthetic speech attacks and how to recognize them. Voice biometrics works with natural conversation and if audio provided does not match the content of the conversation, then actions should be taken

Overall, despite the threat, Corsound can quickly and easisy authenticate customers and stop fraud by identifying synthetic speech. Certainly call centers with voice biometrics and synthetic speech detection are far more protected than those using PINS and passwords which are vulnerable to large scale theft or social engineering.

bottom of page