A comparison of single-stage and two-stage modelling approaches for automatic forensic speaker recognition

In automatic forensic speaker recognition research two frameworks, namely single-stage and two-stage modelling, are used. Although both have their own strengths and limitations, performance is an important attribute that needs to be considered when selecting these methods for forensic research. This...

Full description

Saved in:
Bibliographic Details
Main Authors: Thiruvaran, Tharmarajah, Ambikairajah, Eliathamby, Epps, Julien, Enzinger, Ewald
Format: Conference Proceeding
Language:English
Subjects:
Calibration
Forensics
Frequency modulation
Mel frequency cepstral coefficient
Speaker recognition
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In automatic forensic speaker recognition research two frameworks, namely single-stage and two-stage modelling, are used. Although both have their own strengths and limitations, performance is an important attribute that needs to be considered when selecting these methods for forensic research. This paper compares a calibrated single-stage system with a calibrated two-stage system using a common database in terms of different performance metrics. Neither of the systems provides a consistent advantage over the other in terms of all performance measures, raising the question of whether the use of a two-stage system, which requires additional data and effort, is warranted.
ISSN:2164-7011
2690-3423
DOI:10.1109/ICIInfS.2013.6732023