• The best choice for the company!
    The best choice for the company!

    Speed up and ease the communication with devices around you.

  • Get the best solution for you!
    Get the best solution for you!

    Upgrade the call centers to unseen levels.

  • Let's get work done together.
    Let's get work done together.

    Future arrived here, too. Become a part of it.

  • The best choice for the company!
    The best choice for the company!

    Work even when your eyes or hands are busy.

  • Get the best solution for you!
    Get the best solution for you!

    Future arrived here, too. Become a part of it.

Main objectives and activities

  • The development of flexible text-to-speech synthesis (TTS) of high quality
  • The development of large vocabulary continuous automatic speech recognition (ASR)
  • The research and development of emotion speech recognition
  • The development of speech morphing systems
  • The development of natural language processing modules including dialogue management
  • The application of the developed speech technologies in Western Balkan countries:
    • in multimodal human-machine dialogue systems (IVR, smart phones, smart homes)
    • for purposes such as: text reading, text dictation, speech transcription
    • within aids for the physically disabled, visually impaired, speech impaired, hearing impaired.

The most important innovative results

One can listen to news at a number of speech-enabled web sites (Radio Television of Serbia - RTS, Radio Television of Vojvodina - RTV, eUprava, as well as several municipalities) using a computer or a smart phone. The visually impaired can listen to any text displayed on the screen using the software anReader based on AlfaNumTTS. The AlfaNumASR and AlfaNumTTS components have provided smart phones with basic speech generation and understanding functionalities in Serbian.

Further development of both large vocabulary ASR and more advanced TTS is based on the aforementioned speech and language resources. Both technologies will enable a much wider range of applications and will contribute to the preservation of Serbian and kindred languages in this new domain of communication – spoken dialogue between humans and machines.

 TV antenna

Advertising monitor is a system intended for automatic monitoring of advertisements and musical content in radio and TV stations.

Specified sound recordings are automatically recognized in the received signal and the exact moments of their appearances are logged. Users can get detailed reports on the broadcasting of any audio material, automatically generated by the system based on recognition data.

The system contains a number of FM and TV tuners which receive signals from different radio and TV stations via antennas.

Each of these tuners passes the audio (not the video) signal to a special sound card able to record multiple channels simultaneously. The recordings are compressed as they arrive and archived on local hard disks. Depending on the number of channels recorded and the sizes of hard disks, the archiving period can extend up to several months.

For each search, the administrator defines the search parameters such as target channels, and imports target sound recordings. The search is carried out by independent processes which can be activated on all computers in the system (of which there can be an arbitrary number) and the results are stored in a shared database, which is used to create reports for the clients.

Besides searching for advertisements or musical content, Advertising Monitor can be used for other purposes as well.

 


The software toolkit contains:

  • Applications for recording of audio material
  • Applications for automatic search for given audio content in the recorded audio material
  • Applications for system monitoring and administration.

The system has the following features:

  • Multichannel recording of audio material with compression in real time,
  • Automatic recognition of advertisement, jingles, or songs,
  • Possibility of retroactive monitoring
  • Unlimited system expandability in order to provide faster searches and higher capacities,
  • Automatic deletion of the oldest recordings in order to make room for new ones
  • Quick search by time and date of recording or by station or type of material,
  • Visual representation of the recorded material
  • Possibility of combining the software with the Word Spotter application



AdMonitor scheme

Speech

Speech is the basic means of communication between humans

Using speech, humans can convey their thoughts and feelings to others in a way much more intricate than in any other animal species, and thus the human speech system is the most complicated one...

Read more

ASR

Automatic Speech Recognition

Automatic speech recognition (ASR) is considered one of the greatest technical challenges of today, attracting attention of many researchers worldwide for more than half a century...

Read more

TTS

Text-to-Speech Synthesis

Text-to-Speech Synthesis (TTS) is the oldest speech technology, originating from as early as the 18th century, when first "speaking machines" appeared...

Read more