Company Products Solutions    Services Partners Tech support



4 Krasutskogo str
Saint Petersburg
196084 Russia
tel. +7 812 331-0665
fax: +7 812 327-9297
send a message
Index » Company » Speech technologies
STC has an excellent reputation in high-tech market, designing algorithms for high performance of speech processing applications.

Speech Technology Center develops manufactures and markets software and hardware solutions, standalone devices, DSP boards and software toolkits. STC’s products are based on proprietary patented technologies.

  • Clear Voice – proprietary, original state-of-the-art algorithm which has been developed to automatically
    remove ambient noise from voice and other previously recorded or transmitted sound signals.

  • VoiceCom – algorithms of voice command control for SAPI. Language-independent and speakerindependent technology allows operating computer and other electronic devices by means of voice.

  • Voice Key – voice-based access restriction algorithm. Voice Key authenticates user by voice password and in 0,5 sec time spam allows to identify user and differentiate access rights to information and services.

  • VoiceNet SDK - Speaker-independent and language-independent automatic identification technology.

  • Orator – Speech synthesis application converting text to speech for Russia, without requirement of text preparation beforehand . Various samples of intonation models are used to make this technology “top of the list”. “Orator” is applied in IVR (Interactive Voice Response) systems, inquiry and information services, call-centers and messaging systems, consumer and professional products.

  • Sound Stretcher – technology that allows playback of speech in variable speed (fast/slow) without distorting voice pitch for natural sound. Speed alteration function allows performing the tasks quicker and easier. Sound Stretcher algorithm also allows more efficient use of the advertisement airtime.

  • Reverb Clipper – new technology of reverberation distortions compensation. Increases speech signal clarity recorded indoors with reverberation time up to 3 seconds.

  • Denoiser DSP board – allows integration of modern technology broadband noise filtering in any type of audio processing, transmission or recording equipment.

  • Voice Detect – speech detection algorithm, applied for quick retrieval of speech in lengthy recordings.

  • Jingle Tracker (Music Spotting) - original state-of-the-art algorithm which has been developed to spot music samples in a sound stream. Jingle Tracker allows to spot radio advertisement, report or music composition while on-air.

  • Audio Data Mining – this unique technology allows user to dynamically mine through audio content for specific information without tedious listening of complete file.

  • EdiTracker – state-of-the-art technology of record authentication.

22.04.2008

Over 100 private and governmental audio examiners will come in Denver, CO to participate in the 33d AES Conference. The speeches of participants will be devoted to the current issues of audio authenticity, audio transcription and speaker identification.

more...

18.04.2008

Speech Technology Center will participate in the “Telestrategies ISS World Asia Pacific” Conference that will take place 09-11 June 2008 in Singapore. The event is dedicated to Intelligence Support Systems for Lawful Interception, Criminal Investigations and Intelligence Gathering and will be the world’s largest gathering of Telecom Operators, Law Enforcement, Interior Security and the Intelligence Community to learn and network.

more...

17.04.2008

Automatic Voice Search System Trawl-X has won the Golden Medal of the prestigious industrial award “ZUBR 2008” in the “Information Security” nomination. The committee marked that it is the first Russian automatic voice search system.

more...

Archive news RSS



Subscribe to Newsletter
Speech Technology Center © 2007