A PC Speaker Identification System
نویسنده
چکیده
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.
منابع مشابه
Identivox: a Pc-windows Tool for Text-independent Speaker Recognition in Forensic Environments
A state-of-the-art Gaussian-Mixture-Modelling (GMM) text-independent speaker recognition system has been developed. The system, perfectly suited to the Bayesian approach for Forensic Speaker Recognition, works in a user-friendly platform (Win95/98/NT/2000/me) in a fully user-configurable environment. Speaker modelling, identification and verification are the main functions of the system. The sy...
متن کاملMulti-stage Speaker Diarization for Conference and Lecture Meetings
The LIMSI RT-07S speaker diarization system for the conference and lecture meetings is presented in this paper. This system builds upon the RT06S diarization system designed for lecture data. The baseline system combines agglomerative clustering based on Bayesian information criterion (BIC) with a second clustering using state-of-the-art speaker identification (SID) techniques. Since the baseli...
متن کاملSimilarity Measurement for Speaker Identification Using Frequency of Vector Pairs
Similarity measurement is an important part of speaker identification. This study has modified the similarity measurement technique performed in previous studies. Previous studies used the sum of the smallest distance between the input vectors and the codebook vectors of a particular speaker. In this study, the technique has been modified by selecting a particular speaker codebook which has the...
متن کاملpyannote.metrics: A Toolkit for Reproducible Evaluation, Diagnostic, and Error Analysis of Speaker Diarization Systems
pyannote.metrics is an open-source Python library aimed at researchers working in the wide area of speaker diarization. It provides a command line interface (CLI) to improve reproducibility and comparison of speaker diarization research results. Through its application programming interface (API), a large set of evaluation metrics is available for diagnostic purposes of all modules of typical s...
متن کاملTwo-stage speaker identification system based on VQ and NBDGMM
In this paper, a new speaker identification system is presented. The system can be divided into two subsystems, one close-set speaker identification system and one speaker verification system. The VQ model is used in the close-set speaker identification system and a new method called NBDGMM (Normalization Based on Difference of GMM) is introduced. Experiments have been done to prove that this s...
متن کامل