Speech Technology Center
Speech Technology Center

Speech Technology Center is the leading developer of facial recognition, voice and multimodal biometric systems, as well as solutions for audio and video recording, processing and analysis. With one of the largest R&D teams in the industry and more than 30 years of experience, Speech Technology Center is well known for solutions implemented by some of the largest international companies in banking, security, telecom and public sectors.

The strength of Speech Technology Center’s technology comes from the world-class R&D team that consists of over 150 specialists, including 30 PhDs. Such powerful R&D capability allows us to innovate, quickly respond to changes in the market needs and develop customized top-quality solutions in a timely manner.

Speech Technology Center’s global distribution network includes numerous resellers and partners worldwide. Our products are utilized in over 75 countries.

Training And Consulting In Audio Processing And Analysis

Most Speech Technology Center products include cutting edge technologies and require certain skills from prospective users. That is why we offer special trainings for working with our products. In many cases our software and hardware serve longer than people stay at a company and clients need to train additional users or organize a more advanced training for existing operators.

Obviously, we cover those needs and provide additional trainings on client request. Trainings can take place in our office in Saint Petersburg which is a magnificent city and this provides our visitors with a great chance to see its beauty along with getting the skills needed to use our products. Apart from seeing the city the clients also can get a better understanding of our technologies and capabilities, they can talk directly to our developers and in some cases this kind of interaction has resulted in development of custom products tailored to unique requirements of each customer. When clients choose to have training at our office we help them in obtaining visas, finding suitable accommodation and having a taste of Russian culture by offering guided visits to local sights and points of interest which Saint Petersburg truly abounds.


IKAR Lab 3 is a professional hardware and software solution for advanced speech signal analysis. It provides the capabilities to perform a multitude of valuable audio processing, analysis, audio restoration and voice comparison functions.

IKAR Lab 3 makes possible to perform an in-depth analysis of voice and speech by numerous visualization tools, automated and human-assisted comparison instruments.

IKAR Lab 3 is comprised of advanced and time-tested technologies and algorithms which are already in use at over 450 installations in more than 70 countries world-wide making it the most popular suite of audio processing, analysis and voice biometric matching tools available today. IKAR Lab 3 is available as a software and component hardware only solution or a complete turn-key solution including the workstation hardware, auxiliary equipment and training courses.


Data collection: creating a nation-wide biometric model database with a dedicated processing and control system.

Multimodal search:

  • Automated search for recordings by voice, key words and conversation topics
  • Automatic speech recognition, language and gender identification, diarizaition and voice model tracing
  • Automatic monitoring of the entire audio data flow with user notification of target voices being detected
  • Search by biometric face model in videostream and by photo in a video archive containing face biometric models
  • Notification: The operator gets a notification the moment a match with the database is found


Forensic analysis:

  • Full pack of experts comparison methods: formant, pitch and auditory analysis;
  • Speech and noise detection;
  • Editing and processing of sound recordings;
  • Video player with editable audio and video tracks;
  • Automatic video indexing and image quality improvement;
  • Automatic text transcription and segmentation by speakers (up to five) in a dialog/polylogue.
  • Report generation and monitoring performance of users and systems

Voicegrid RT

The VoiceGridTM RT application is designed for speaker identification. The system allows sorting all the records in accordance with target speakers’ voice samples. The minimal configuration allows investigators to process up to 10,000 incoming recordings per day against a list of up to 100 targets.

The VoiceGridTM RT voice matching, along with the entire VoiceGridTM product line, uses STC exclusive analysis tools, including processing, segmentation, feature extraction and identification of voice samples.

Voicegrid X

VoiceGrid X is a high-end application for speaker voice identification in large audio databases.


  • VoiceGrid X is an essential solution for security staff:
  • It prevents call center frauds.
  • It Increases internal investigation efficiency by using recorded calls.

Why use VoiceGrid X?

VoiceGrid X enables you to significantly enhance analysis of audio recordings. VoiceGrid X processes speaker voices in recordings and automatically skips audio files without specified voice features. Release your call center agents from time-consuming work with VoiceGrid X.

VoiceGrid™ RT: Sophisticated Distributed Solution for Real-time Speaker Identification
VoiceGrid X: an Application for Voice Identification in Multiple Audio Files

How is it possible?

VoiceGrid X is an out-of-the-box voice biometric solution designed by Speech Technology Center. Biometric technology enables you to analyze biological features of a person (e.g. fingerprints that are the most common biometric features nowadays). As for voice biometrics, it is able to measure voices and compare them against each other in order to identify a person or verify such person’s identity.

Speech Technology Center
Biometric Systems, Gnome Digital Audio Recorders & Smart Logger II

Solutions Africa

Solutions Middle East & India

Solutions South Africa