Voice biometrics from Speech Technology Center comes to development business



15 March 2021 — The Speech Technology Center (part of the Sberbank ecosystem) and the Samolet Group are implementing the first voice biometrics project in the development industry to identify customers by voice in order to improve the quality of service in the call centre of the Samolet Group, a major developer in the Moscow region.

Voice biometrics augmented by intelligent speech analytics with emotion recognition, will help identify by voice the customers contacting the call centre and create the most effective and emotionally comfortable dialogue as early as at the call stage. In the future, regardless of the telephone number used to place the call, the customer could be immediately connected with the personal manager, without any involvement of the operator, in order to initiate a dialogue based on previous communication experience and preferences, preserving the context of past communications. This will eliminate long waiting times on the line and unnecessary switching to save the customer's most valuable resource — his/her time — by demonstrating customer care and a new level of service. Samolet Group expects that the introduction of voice biometrics will improve customer loyalty and generate additional sales of up to RUB 500 million a year.

The introduction of voice biometrics marks the expansion of collaboration between the Speech Technology Center and the Samolet Group. The first joint project was the deployment of an intelligent customer management system to improve the effectiveness and quality of sales. Three months after the launch, the project demonstrated its first results: the time from initial meeting to contract signing was cut by 14%, and the number of sales actions per manager jumped by 21%. Speech analytics from Speech Technology Center already implemented in the call centre of Samolet Group's sales department considers a wide range of dialogue characteristics allowing to quickly assess the quality of responses, identify the reasons for long-term service and the level of knowledge among employees. Speech analytics enables 24/7 operations and allows shifting from random checks (1–3%) to 100% assessment of dialogues to hear the voice of each customer. In Samolet Group, the sales reps of the call centre handle more than 10 thousand calls related to real estate purchases every month. For quality control purposes, all dialogues are recorded and automatically converted into text in the 'customer-operator' format with a second-by-second timeline. This data is then submitted for further analysis. Samolet Group expects that speech analytics will help bring the conversion from calls to sales office visits up to 75% as early as in 2021, improving the end-to-end conversion rate.

Olga Balagurova, Director of Customer Service, Samolet Group: 'We are closely following the trends of digitalisation in terms of what is being developed and implemented in the most advanced industries. Our goal is to build customer-centric business processes and create products and services based on real customer needs. To do so, we opted for the solutions offered by Speech Technology Center, as the speech analytics from Speech Technology Center demonstrated the maximum depth of analysis (with more than 40 parameters), as well as the best figures of customer speech recognition, including the speech with background noise or partially unintelligible speech. In addition, the system allows transcribing the entire dialogue with the customer into not just keywords but a complete text. The introduction of voice biometrics will enable us to handle 100% of incoming calls with high quality, promptly resolve customer enquiries and cut the time of communication by 30%, which is especially valued by customers today. The key benefit of collaboration with Speech Technology Center is the ability to integrate an entire stack of AI solutions from one vendor with strong experience in enterprise-level projects. This ensures that we can be confident in the quality of products and their integration with each other'.

Voice biometrics is one of the four pillars of the innovative call centre, which the Samolet Group wants to complete this year. Alongside, the company is introducing an omnichannel platform as a framework for the development of its digital services: Whatever the way and sequence used by the customer to communicate with the company (telephone, chat or social media), the history of these communications will be preserved and the dialogue will resume where it stopped next time the customer makes the call. The automatic speech-to-text conversion followed by speech analysis allows to identify trends in the customer's needs and wants, including those that the customer is not aware of.

Dmitriy Dyrmovskiy, CEO of Speech Technology Center: 'Today, high-quality remote service is no longer a trend, but a standard. The share of remote operations is expanding, while businesses raise their requirements in terms of profitability, and the customers demand more in terms of quality of service. Our Customer Engagement Platform helps the managers of large call centres and IT directors to cut the operating costs of their call centres, improve customer service and increase sales by developing their business activities and hearing the voice of their customer'.

About Speech Technology Center: Speech Technology Center (part of the Sber ecosystem) is a global developer of intelligent speech and face recognition technologies, and an expert resource in AI and machine learning, a member of ESSMA. Speech Technology Center is one of the few companies in the world that creates and develops both biometric modalities: face and voice. The voice falsification detection and speech recognition solutions developed by Speech Technology Center score leading positions in global rankings by NIST, ASVspoof Challenge, VOiCES. At CHiME Сhallenge 2020, its speech recognition technology was recognized as the best. Speech Technology Center’s solutions are in demand in 70 countries around the world.

Official website: www.speechpro.com

Media contact: pr@speechpro.com