Precise technology

OF SOUND DECOMPOSITION

Our technology concentrates on sound decomposition quality enhancement, mainly due to our achievement of the unparalleled resolution and continuity of sound spectrum. Sound Objects extracted from the spectrum incorporate specific parameters allowing for successful segmentation (assigning them to a particular sound source) and separation (precise disjunction and reconstruction of overlapping Sound Objects in case of sounds of the same frequency).

mikrofon

New possibilities

OF AUTOMATIC SOUND SOURCES SEPARATION

The sound-into-sound-objects decomposition algorithms allow to separate automatically co-sounds whose frequencies differ only by 4% (around one semi-tone). Such precision of sound components separation allows for previously unattainable ability to recognize logical components of all sound sources as well as precision of their isolation.

Such precision of sound components separation together with preserved information about frequency, amplitude, position and phase of each Sound Object allows for previously unattainable ability to recognize logical components of all sound sources as well as precision of their isolation.

mac

Potential Applications

OF SOUND SEPARATION

Extraordinary quality

IN SOUND SIGNAL ANALYSIS

With specially designed algorithms, we are able to decompose an acoustic signal into vectorial Sound Objects and begin to group them according to their source.

Precise Sound Separation

BASED ON SOUND OBJECTS

ic10

FILTERS

Unlike the traditional methods of sound processing such as fast Fourier transform (FFT) and its derivatives (DCT,  CQT), our technology engages uniquely designed bank of filters in order to obtain vectorial Sound Objects carrying information about precise parameters depicting the signal.

ic12

SPECTRUM

The spectrogram achieved in the process of signal filtration, allows for precise separation of overlapping-in-time frequencies, which differ barely >4% (1 semitone). Moreover, it can be characterized by a unchangeable resolution in all 500 logarithmic frequency ranges.

ic11

VECTORS

By the use of our algorithms we are able to identify  Sound Objects and begin to group them according to their source.