Call center: this AI imitates the customer’s accent to gain their trust

Imagine this scene, a Parisian teleoperator contacts a potential customer in Marseille. In just a few seconds, he loses the accent of the capital in favor of that of the south-east thanks to a system that combines recognition and voice synthesis. This story is not yet a reality in France, but it could happen in the United States where the startup Sanas has developed this device.

Tests are carried out all over the world

Concretely, a machine learning algorithm is able to quickly recognize the accents of two interlocutors. In just a few words, the operator’s speech is changed and the result is striking as can be heard in this presentation video.

According to Techcrunch, Sanas is currently carrying out experiments in the United States, the United Kingdom, the Philippines, India, or even in Latin America and the AI ​​recognizes the accents of American, Spanish, British, Indian, Filipino and soon to be Australian.

As our colleagues point out, the system is not yet perfect, and the voice still sounds very artificial, however this technology continues to improve during the test phases. Enough to convince several investments that allowed the company to make a funding round of $ 5.5 million.

Quoted by the American media, the CEO of the company, Maxim Serebryakov, specifies: ” Sanas strives to make communication easy and frictionless, so that people can speak with confidence and understand each other, wherever they are and whoever they are trying to communicate with. ».

Moreover, artificial intelligence is inviting itself more and more into the profession of teleoperator. In 2019, Google even supported a project called CallJoy. This AI was doing the job of a switchboard operator by answering customer calls directly. The latter was intended primarily for small traders and was supposed to make appointments. A little over a year later, the Mountain View firm decided to put an end to this experience.

Source Link

Share this article:

Leave a Reply

most popular