Forensic speaker recognition using traditional features comparing automatic and human-in-the-loop formant tracking
Entity
UAM. Departamento de Ingeniería InformáticaPublisher
International Speech Communication AssociationDate
2009-09Citation
10th Annual Conference of the International Speech Communication Association. September 6-10, 2009ISSN
2308-457XFunded by
This work has been funded by the Spanish Ministry of Education under project TEC2006-13170-C02-01.Editor's Version
http://www.isca-speech.org/archive/interspeech_2009/i09_2343.htmlSubjects
automatic formant tracking; forensic speaker recognition; traditional features; likelihood ratio; Informática; TelecomunicacionesNote
Proceedings of Interspeech 2009, Brighton (United Kingdom)Rights
© 2009 ISCAAbstract
In this paper we compare forensic speaker recognition with traditional features using two different formant tracking strategies: one performed automatically and one semi-automatic performed by human experts. The main contribution of the work is the use of an automatic method for formant tracking, which allows a much faster recognition process and the use of a much higher amount of data for modelling background population, calibration, etc. This is especially important in likelihood-ratio-based forensic speaker recognition, where the variation of features among a population of speakers must be modelled in a statistically robust way. Experiments show that, although recognition using the human-in-the-loop approach is better than using the automatic scheme, the performance of the latter is also acceptable. Moreover, we present a novel feature selection method which allows the analysis of which feature of each formant has a greater contribution to the discriminating power of the whole recognition process, which can be used by the expert in order to decide which features in the available speech material are important.
Files in this item
Google Scholar:Castro, Alberto de
-
Ramos Castro, Daniel
-
González Rodríguez, Joaquín
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.