Speech Technology Center announces AI-based solution for corporate meeting minutes

July 1, 2021, Moscow — Speech Technology Center announces Nestor.BRIEF, a new AI-based product for logging in-person and online meetings. The solution enables speech-to-text conversion and supports a single digital archive for meeting notes. Using this solution from Speech Technology Center enables you to digitize meeting notes and reduce time spent on minutes preparation by at least 50 percent. It simplifies saving and searching for data from any meeting.
This is an ideal solution for companies that prioritize enterprise communication security, data protection, and workplace digitalization.
The program allows for integration with video conferencing platforms TrueConf and VideoMost, while integration with top 5 video conferencing systems is currently in the works.

Dmitriy Dyrmovskiy, CEO of Speech Technology Сenter, notes that, 'In today's business processes, often more than 50% of time is devoted to meetings and appointments, while communications have remained an important, though non-digitized element. Time-consuming preparation of meeting notes reduces efficiency, as it requires routine manual work and forces managers to spend valuable time reminding employees of the assignments. At the same time, colleagues who miss meetings are completely devoid of context. All of that has a negative impact on business and corporate culture. This new Speech Technology Сenter solution helps address these issues and develop a single digital workplace with easy automation and workflow controls via user-friendly interfaces. We have already implemented simple integrations with a number of well-known conference systems. In addition to speech recognition for the Russian language, the Speech Technology Сenter's product supports English and Spanish, with Arabic and other languages in the pipeline. Language localization will allow scaling the product to the global market'.

As the number of online, offline, and hybrid (mixed) meetings in organizations grows, there is strong demand for recording and storing important information in a single, secure place.

This Speech Technology Сenter solution enables speakers' speech-to-text conversion and forms a digital minutes archive with intuitive objects, where text, audio, and video are combined. Any authorized employee/meeting participant can see who said what and when, regardless of the meeting type: offline — held in a meeting room, or online — conducted via video conferencing, or mixed format.

 Key benefits of this solution:

  • enhanced speech recognition model for the Russian language, including recognition of spontaneous and quite intelligible speech. The Speech Technology Сenter's speech recognition technology was recognized as the best in the world as part of the CHIME-2020 independent international competition
  • Vocabulary training for unique/specialized tasks: the product comes with a built-in module for updating vocabulary based on corporate materials. It allows companies to add internal documents or individual words: names, abbreviations, slang, and/or technical terms — everything that is not common in Russian language, but is used in a particular organization
  • Active management of meetings: during the recording you can add tags to structure information, enabling a quick search for the necessary data later on
  • Automated handling of online-meeting recordings. The system "understands" where to find the record and performs the recognition, providing results for employees in the shortest possible time
  • Seamless integration with popular audio and video conferencing systems. Recording and speech-to-text conversion for offline meetings using existing systems and microphones
  • Integration with third-party solutions via API
  • Web interface and mobile application
  • Installation typically takes no more than one week

In the future, it will be possible to arrange tasks during the meeting and track progress, as well as follow the meeting even on mute: subtitles will be available to help stay focused. 

This Speech Technology Сenter solution offers a private logging system, so it can be used by organizations with critical requirements for communications security and data protection. In particular, this will benefit large companies, state corporations, federal ministries and agencies, regional administrations and ministries, city administrations as well as regional centers.

Speech Technology Center is a global developer of products and solutions based on conversational artificial intelligence, machine learning, and computer vision with 30 years of experience. It offers technological expertise in speech technology, as well as facial recognition and voice biometrics. Speech Technology Center Group is focused on creating B2B and B2G AI solutions, with more than 5,000 AI projects completed around the world, including national-scale projects in Mexico, Ecuador, and the Middle East. In Russia, Speech Technology Center solutions are put to use in the largest banks, telecommunications companies, the fuel and energy sector, as well as the public sector. Moreover, they are being used to introduce the Safe&Smart city concept. Speech Technology Center Group’s voice forgery detection and speech recognition technology are on top of the global rankings like NIST, ASVspoof Challenge, VOiCES, and CHiME Challenge.