Topological voiceprints for speaker identification

Despite its noninvasive nature, subject identification by voice is not as popular as other biometric procedures (i.e. fingerprinting). In part, this is due to the difficulty of establishing how close is close enough when comparing spectral features. In this work, we address this issue by showing how...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Trevisan, Marcos Alberto, Eguia, Manuel Camilo
Publicado: 2005
Materias:
Biometrics
Speaker recognition
Topological indexes
Deformation
Ergonomics
Integer programming
Modulation
Oscillations
Pressure effects
Cross-counting algorithms
Power spectrum
Speech segments
Voiceprints
Spectrum analysis
Acceso en línea:https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_01672789_v200_n1-2_p75_Trevisan
http://hdl.handle.net/20.500.12110/paper_01672789_v200_n1-2_p75_Trevisan
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id paper:paper_01672789_v200_n1-2_p75_Trevisan
record_format dspace
spelling paper:paper_01672789_v200_n1-2_p75_Trevisan2025-07-30T17:55:06Z Topological voiceprints for speaker identification Trevisan, Marcos Alberto Eguia, Manuel Camilo Biometrics Speaker recognition Topological indexes Deformation Ergonomics Integer programming Modulation Oscillations Pressure effects Cross-counting algorithms Power spectrum Speech segments Voiceprints Spectrum analysis Despite its noninvasive nature, subject identification by voice is not as popular as other biometric procedures (i.e. fingerprinting). In part, this is due to the difficulty of establishing how close is close enough when comparing spectral features. In this work, we address this issue by showing how to characterize spectra by means of sets of integers, borrowing topological tools used in the theory of dynamical systems. On the other hand, we report an empirical result: within a relatively small bank of speakers, there are subsets of integers that seem to strenghten the speakers' identity information. These results suggest a new direction in the identification of subjects by voice: one in which arrangements of integers define voiceprints that stand on their own, despite any acceptance/rejection thresholds. © 2004 Elsevier B.V. All rights reserved. Fil:Trevisan, M.A. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Eguia, M.C. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. 2005 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_01672789_v200_n1-2_p75_Trevisan http://hdl.handle.net/20.500.12110/paper_01672789_v200_n1-2_p75_Trevisan
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic Biometrics
Speaker recognition
Topological indexes
Deformation
Ergonomics
Integer programming
Modulation
Oscillations
Pressure effects
Cross-counting algorithms
Power spectrum
Speech segments
Voiceprints
Spectrum analysis
spellingShingle Biometrics
Speaker recognition
Topological indexes
Deformation
Ergonomics
Integer programming
Modulation
Oscillations
Pressure effects
Cross-counting algorithms
Power spectrum
Speech segments
Voiceprints
Spectrum analysis
Trevisan, Marcos Alberto
Eguia, Manuel Camilo
Topological voiceprints for speaker identification
topic_facet Biometrics
Speaker recognition
Topological indexes
Deformation
Ergonomics
Integer programming
Modulation
Oscillations
Pressure effects
Cross-counting algorithms
Power spectrum
Speech segments
Voiceprints
Spectrum analysis
description Despite its noninvasive nature, subject identification by voice is not as popular as other biometric procedures (i.e. fingerprinting). In part, this is due to the difficulty of establishing how close is close enough when comparing spectral features. In this work, we address this issue by showing how to characterize spectra by means of sets of integers, borrowing topological tools used in the theory of dynamical systems. On the other hand, we report an empirical result: within a relatively small bank of speakers, there are subsets of integers that seem to strenghten the speakers' identity information. These results suggest a new direction in the identification of subjects by voice: one in which arrangements of integers define voiceprints that stand on their own, despite any acceptance/rejection thresholds. © 2004 Elsevier B.V. All rights reserved.
author Trevisan, Marcos Alberto
Eguia, Manuel Camilo
author_facet Trevisan, Marcos Alberto
Eguia, Manuel Camilo
author_sort Trevisan, Marcos Alberto
title Topological voiceprints for speaker identification
title_short Topological voiceprints for speaker identification
title_full Topological voiceprints for speaker identification
title_fullStr Topological voiceprints for speaker identification
title_full_unstemmed Topological voiceprints for speaker identification
title_sort topological voiceprints for speaker identification
publishDate 2005
url https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_01672789_v200_n1-2_p75_Trevisan
http://hdl.handle.net/20.500.12110/paper_01672789_v200_n1-2_p75_Trevisan
work_keys_str_mv AT trevisanmarcosalberto topologicalvoiceprintsforspeakeridentification
AT eguiamanuelcamilo topologicalvoiceprintsforspeakeridentification
_version_ 1840328041729884160

Ejemplares similares