With the help of the automatic Kazakh speech recognitions system, speech input of alphanumeric data to the computer can be performed. This system has three main working modes:
- Continuous-speech recognition;
- Separate voice-command recognition;
- Voice speaker identification.
For continuous-speech recognition, a human reads a selectable text in Kazakh into the microphone, while the computer types it on its screen. There is an option of saving the text typed as a separate file, its further edition, sending via electronic mail and performing any other typical text operations. The automatic speech recognition system can give effectual help in any situations, in which it is necessary to transfer speech into electronic text representation: steno typing of speeches, meetings, monologues, and phone conversations.
The separate voice command recognition mode can be used to control various devices, for example, household appliances or robots.
The voice speaker identification mode can be used in systems of information security and access control. In this mode, the recognition system indentifies the personality of a human on the basis of a short key phrase articulated by him/her.
Application of the speech synthesis and recognition systems developed by our company gives the opportunity of creating computer systems capable of conducting a dialogue with a user in the natural Kazakh language.
The principal fields of application of our speech technologies are the following:
- Robotic engineering
- Speaking smart devices
- “Smart House”
- Language teaching systems
- “Voice Translators”
- Audio books
- Telephony systems (Call-centers)
- Information booths
- Information security systems
- Voice criminalistic examination
- Dumb and blind help systems
Duty: 09-00 – 18-00
The information presented on this website can be copied and used without limits provided that a link to this website is given.