AIPlugins: software set of plug-ins

Software set of plug-ins that allow to automate speakers identification process.

Automatic Speaker Identification
AI Plugins
Product Library:

Overview

The AI Plug-Ins for SIS II allow for automated speaker identification. AI Plug-ins enables the calculation of speech signal characteristics to determine the suitability of a recording for identification purposes. The user is provided with information on the reliability of each identification method on result received from the processed characteristics. The calculation of speech signal characteristics may be determined for either a segment or the entire signal. Signal to noise ratio method may be accomplished in any frequency range. The speech detection plug-in automatically reveals the fragments of speech suitable for identification.

 

Features

  • Automatic calculation of speech signal characteristics: assesses the suitability of a recording for identification purposes
  • Automatic marking of speech sections of a phonogram suitable for identification.
  • Automatic comparison of two speakers using 3 automatic identification algorithms with overall conclusion.
  • Automatic detection of clicks, pops, clipped fragments of phonogram and other types of noises.
  • Operating instructions

 

 

Technical specification

Supported file formats all formats in case proper codecs are installed (*.WAV, *.MP3, *.WMA, *.AVI )
Minimum duration of signal 3 seconds of clear speech
Signal to noise ratio not less than 10 dB
Methods of processing 3