A PC speaker identification system for forensic use: IDEM

 The field of Speaker Identification in forensic is one of the oldest application of speech science. Listening test and spectrogram reading have been the most popular approach in this specific task for many years. We introduce a method based on the comparison of vowel formant, and we describe the associated software tools that let you easily perform a complete speaker identification test: starting from speech acquisition and ending with a report on statistical tests. The system has been designed to run on a small computer, and in a user-friendly environment. After a first release of IDEM in 1991[1] we have now reached a (almost) errors free and "enduser" robust version of the system. We base our corrections and improvements of the system on our own experience in this field, and on the suggestions of real users, i.e. of several police investigation bureau that extensively use the IDEM system.

[1]  Andrea Paoloni,et al.  Comparison between automatic methods and human listeners in speaker recognition tasks , 1989, EUROSPEECH.

[2]  Andrea Paoloni,et al.  A new automated method for reliable speaker identification and verification over telephone channels , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Andrea Paoloni,et al.  Bayesian decision in the speaker recognition by acoustic parametrization of voice samples over telephone lines , 1993, EUROSPEECH.

[4]  B. Saverione,et al.  ARES: An environment for speech analysis and labelling , 1989, Proceedings. Electrotechnical Conference Integrating Research, Industry and Education in Energy and Communication Engineering',.

[5]  Nikos Fakotakis,et al.  A text-independent speaker recognition system based on vowel spotting , 1993, Speech Commun..