top of page
speaker_diarz.PNG

Different Colours for different Speakers

Speaker Diarization

Automatic Speaker Diarization refers to separation of speaker’s talk from the audio. The software is language independent. The police get hold of some disputed audio. It may contain the voice of 2 or more speakers. In order to compare the voice of culprit
with the voice in disputed voice, there is a need to separate the voices into different audio files.
The system options: The system has unsupervised diarization option which detects the number of speakers automatically and does the diarization. The analyst can do the listening test and find the number of speakers too. The system has a facility for 2 speaker, 3 speaker and 4 speaker diarization. If the number of speakers is more than 4, use manual speaker diarization. It also
provides SNR (Signal to Noise Ratio) measurement and gender detection after diarization.

salient features of the system:

  • ASD4000 is automatic speaker diarization​  system useful for diarization of 2, 3 and 4  speakers

  • It has unsupervised mode that automatically detects number of speakers in the audio and diarizes the audio.

  • It also has separate 2 speaker, 3 speaker and 4 speaker diarization options.

  • It provides manual diarization facility in case the number of speakers exceed 4.

  • It has a facility to find SNR of any audio.

  • It provides facility of gender detection for each audio after diarization.

  • There is a facility for all types of basic audio processing like record, play, export, split stereo channels, zoomin, zoomout, audio processing like normalize, show clipping with opening and closing of windows and changing their layout etc.

  • All above features are supported for mono as well as stereo files of any formats and extensions. Facility to run on the device as a complete offline solution.

bottom of page