Audio Recognition Engine
DISCOVER SOUND GENETICS
Each sound leaves a “vocal imprint” that our brain is able to analyze and categorize.
But what happens if the audio is disturbed or if we don’t recognize that sound, that language, that voice? From that data we are no longer able to obtain useful information.
Pragma Etimos starts from the genetics of sound, reconstructing the DNA, the true essence of sound, “from the vocal imprint”, made up of several “Audiosomes”, and returns information on which to base your analyzes.
In particular, we distinguish two concepts:
– Audiosoma: a unique identifier that helps to compose the imprint of voice audio/sound.
– Audioma: summation of Audiosomes that make up the vocal/sound imprint.
Use the intelligent optimization and recognition algorithms.
– Voiceprint identification
– Diarization of the speakers
– Language identification
– Gender identification
– Age estimate
– Voice activity detection
– Estimation of speech quality
– Get useful investigation data even from noisy and poor quality audio
– Receive additional information from the analysis of audio files
Our solutions are available for different architectures:
– Web Services
Write us for more information or to request a quote. Our team will reply as soon as possible.
Pragma Etimos S.r.l.
Via Dei Bersaglieri, 5
Aprilia, LT 04011