Translated with AI from the Russian original.
Business representatives will be able to analyze recordings of offline dialogues between employees and customers in bank offices, stores, clinics, and other organizations using neural networks.
The Yandex SpeechSense update expands marketing analytics capabilities: businesses will be able to determine customer loyalty, the effectiveness of marketing offers, and find the most successful examples of handling objections. It will also allow for a comprehensive assessment of an employee's work, for example, to determine whether customers like their communication style, which words and phrases should not be used, and which, on the contrary, can lead to a deal.
Yandex Cloud explained:
Usually, when evaluating offline communications, companies analyze only the speech of their employee using audio badges, because when several people are talking, systems often cannot determine which of the interlocutors owns a particular remark.
Yandex SpeechSense solves this problem using the YandexGPT neural network and Speaker Labeling technology. They separate the remarks in the dialogue from each other and then distribute them by roles. Thus, companies can use audio recordings from various recording devices for speech analytics and see the results of the analytics in the context of the employee and the client.
