Challenge.

Synthesize and Analyze
The application was to be able to distinguish various voices in a shared space by analyzing and segmenting specific sequences directly from raw data based on certain parameters defined in the algorithm. Further the final intelligence would be capable of recognizing the number of different voice frequencies and to recognize them each time someone else speaks in the room. The challenge of the application development was to show in the application graph redistribution of specific speakers which participated in the conversation and to recognize their involvement and their voices in real-time. Technologies used in the development process of the application were: C++ and Android Studio.

Solution.

Refine and Conclude
Based on the needs and requests from the client, the team quickly got involved into researching about  voice recognition and the voice processing. The requirements from the client were to have the ability to register as many  voice frequencies as possible in one place and to collect data about these voices and their frequencies. An innovative algorithm was created able to recognize voices in one place and make the communication between Android UI and the backend system (RESTful services). The user interface was created able to give names to different speakers in the room and to recognize them by marking their voice every time they spoke.

Challenge.

Synthesize and Analyze
The application was to be able to distinguish various voices in a shared space by analyzing and segmenting specific sequences directly from raw data based on certain parameters defined in the algorithm. Further the final intelligence would be capable of recognizing the number of different voice frequencies and to recognize them each time someone else speaks in the room. The challenge of the application development was to show in the application graph redistribution of specific speakers which participated in the conversation and to recognize their involvement and their voices in real-time. Technologies used in the development process of the application were: C++ and Android Studio.

Solution.

Refine and Conclude
Based on the needs and requests from the client, the team quickly got involved into researching about  voice recognition and the voice processing. The requirements from the client were to have the ability to register as many  voice frequencies as possible in one place and to collect data about these voices and their frequencies. An innovative algorithm was created able to recognize voices in one place and make the communication between Android UI and the backend system (RESTful services). The user interface was created able to give names to different speakers in the room and to recognize them by marking their voice every time they spoke.
Speech recognition and voice processing has incredible potential to be developed further in the future, as they are hot topics not just in the IT world, but also in other fields including neural networks, health care, education, and military.
Gartner identified top 10 strategic IT technology trends in which one of them is in the field of speech recognition. Its expansion is expected in the next few years. This project allowed the team to further expand their knowledge in the field of voice processing and speech recognition opening doors to new possibilities and future innovations.

Key Facts.

Speech recognition and voice processing has incredible potential to be developed further in the future, as they are hot topics not just in the IT world, but also in other fields including neural networks, health care, education, and military.
Gartner identified top 10 strategic IT technology trends in which one of them is in the field of speech recognition. Its expansion is expected in the next few years. This project allowed the team to further expand their knowledge in the field of voice processing and speech recognition opening doors to new possibilities and future innovations.