CIVIL Corpus: Voice Quality for Speaker Forensic Comparison
Loading...
Official URL
Full text at PDC
Publication date
2013
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier
Citations
Exportar
Citation
Segundo, Eugenia San, et al. «CIVIL Corpus: Voice Quality for Speaker Forensic Comparison». Procedia - Social and Behavioral Sciences, vol. 95, octubre de 2013, pp. 587-93. DOI.org (Crossref), https://doi.org/10.1016/j.sbspro.2013.10.686.
Abstract
The most frequent way in which criminals disguise their voices implies changes in phonation types, but it is difficult to maintain them for a long time. This mechanism severely hampers identification. Currently, the CIVIL corpus comprises 60 Spanish speakers. Each subject performs three tasks: spontaneous conversation, carrier sentences and reading, using modal, falsetto and creak(y) phonation. Two different recording sessions, one month apart, were conducted for each speaker, who was recorded with microphone, telephone and electroglottography. This is the first (open-access) corpus of disguised voices in Spanish. Its main purpose is finding biometric traces that remain in voice despite disguise.
Description
This research has been made possible by grants awarded by the Spanish Ministry of Science and Innovation (FFI10-21690/Cualidad de voz), Spanish Ministry of Education (Beca FPU Programa Nacional de Formación de Profesorado Universitario, BOE 11-07-2009) and the Spanish National Research Council-CSIC (Jae-Predoctoral-Junta para la Ampliación de Estudios, BOE 03-06-2011).