Observatorio de I+D+i UPM

Descripción
Phonation distortion leaves relevant marks in a speaker's biometric pro?le. Dysphonic voice production may be used for biometrical speaker characterization. In the present paper phonation features derived from the glottal source (GS) parameterization, after vocal tract inversion, is proposed for dysphonic voice characterization in Speaker Veri?cation tasks. The glottal source derived parameters are matched in a forensic evaluation framework de?ning a distance-based metric speci?cation. The phonation segments used in the study are derived from ?llers, long vowels, and other phonation segments produced in spontaneous telephone conversations. Phonated segments from a telephonic database of 100 male Spanish native speakers are combined in a 10-fold cross-validation task to produce the set of quality measurements outlined in the paper. Shimmer, mucosal wave correlate, vocal fold cover biomechanical parameter unbalance and a subset of the GS cepstral pro?le produce accuracy rates as high as 99.57 for a wide threshold interval (62.08-75.04%). An Equal Error Rate of 0.64 % can be granted. The proposed metric framework is shown to behave more fairly than classical likelihood ratios in supporting the hypothesis of the defense vs that of the prosecution, thus o?ering a more reliable evaluation scoring. Possible applications are Speaker Veri?cation and Dysphonic Voice Grading.
Internacional	Si
JCR del ISI	Si
Título de la revista	Language and Law
ISSN	2183-3745
Factor de impacto JCR
Información de impacto
Volumen	1
DOI
Número de revista	2
Desde la página	42
Hasta la página	66
Mes	SIN MES
Ranking

Esta actividad pertenece a memorias de investigación

• Autor: Pedro Gomez Vilda (UPM)
• Autor: Eugenia San Segundo (University of York)
• Autor: Luis Miguel Mazaira Fernández (Independiente)
• Autor: Agustin Alvarez Marquina (UPM)
• Autor: M. Victoria Rodellar Biarge (UPM)

• Creador: Centro o Instituto I+D+i: Centro de tecnología Biomédica CTB