Limits...
Improving Speaker Recognition by Biometric Voice Deconstruction.

Mazaira-Fernandez LM, Álvarez-Marquina A, Gómez-Vilda P - Front Bioeng Biotechnol (2015)

Bottom Line: The present study benefits from the advances achieved during last years in understanding and modeling voice production.The paper hypothesizes that a gender-dependent characterization of speakers combined with the use of a set of features derived from the components, resulting from the deconstruction of the voice into its glottal source and vocal tract estimates, will enhance recognition rates when compared to classical approaches.Experimental validation is carried out both on a highly controlled acoustic condition database, and on a mobile phone network recorded under non-controlled acoustic conditions.

View Article: PubMed Central - PubMed

Affiliation: Neuromorphic Voice Processing Laboratory, Center for Biomedical Technology, Universidad Politécnica de Madrid , Madrid , Spain.

ABSTRACT
Person identification, especially in critical environments, has always been a subject of great interest. However, it has gained a new dimension in a world threatened by a new kind of terrorism that uses social networks (e.g., YouTube) to broadcast its message. In this new scenario, classical identification methods (such as fingerprints or face recognition) have been forcedly replaced by alternative biometric characteristics such as voice, as sometimes this is the only feature available. The present study benefits from the advances achieved during last years in understanding and modeling voice production. The paper hypothesizes that a gender-dependent characterization of speakers combined with the use of a set of features derived from the components, resulting from the deconstruction of the voice into its glottal source and vocal tract estimates, will enhance recognition rates when compared to classical approaches. A general description about the main hypothesis and the methodology followed to extract the gender-dependent extended biometric parameters is given. Experimental validation is carried out both on a highly controlled acoustic condition database, and on a mobile phone network recorded under non-controlled acoustic conditions.

No MeSH data available.


DET curves comparing classical parameters in a gender-independent setup with the GDEB parameterization on ALBAYZIN development set for male (left) and female (right) speakers.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4585141&req=5

Figure 6: DET curves comparing classical parameters in a gender-independent setup with the GDEB parameterization on ALBAYZIN development set for male (left) and female (right) speakers.

Mentions: DET curves corresponding to the results presented in Table 3 are depicted in Figure 6 for both male and female speakers. Clearly, the parameterization generated by the GDEB front-end, in this case just including information from the GSE in the form of MFCC, is the one providing the best results on the development set for male and female speakers. It must be reminded that the goal of the test is the reduction of EER and not the area under the curve (AUC), thus it may happen that GIC shows better results than GDC for some of the points of the curve. However, GDC will always produce better or at least equal results than GIC in terms of EER.


Improving Speaker Recognition by Biometric Voice Deconstruction.

Mazaira-Fernandez LM, Álvarez-Marquina A, Gómez-Vilda P - Front Bioeng Biotechnol (2015)

DET curves comparing classical parameters in a gender-independent setup with the GDEB parameterization on ALBAYZIN development set for male (left) and female (right) speakers.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4585141&req=5

Figure 6: DET curves comparing classical parameters in a gender-independent setup with the GDEB parameterization on ALBAYZIN development set for male (left) and female (right) speakers.
Mentions: DET curves corresponding to the results presented in Table 3 are depicted in Figure 6 for both male and female speakers. Clearly, the parameterization generated by the GDEB front-end, in this case just including information from the GSE in the form of MFCC, is the one providing the best results on the development set for male and female speakers. It must be reminded that the goal of the test is the reduction of EER and not the area under the curve (AUC), thus it may happen that GIC shows better results than GDC for some of the points of the curve. However, GDC will always produce better or at least equal results than GIC in terms of EER.

Bottom Line: The present study benefits from the advances achieved during last years in understanding and modeling voice production.The paper hypothesizes that a gender-dependent characterization of speakers combined with the use of a set of features derived from the components, resulting from the deconstruction of the voice into its glottal source and vocal tract estimates, will enhance recognition rates when compared to classical approaches.Experimental validation is carried out both on a highly controlled acoustic condition database, and on a mobile phone network recorded under non-controlled acoustic conditions.

View Article: PubMed Central - PubMed

Affiliation: Neuromorphic Voice Processing Laboratory, Center for Biomedical Technology, Universidad Politécnica de Madrid , Madrid , Spain.

ABSTRACT
Person identification, especially in critical environments, has always been a subject of great interest. However, it has gained a new dimension in a world threatened by a new kind of terrorism that uses social networks (e.g., YouTube) to broadcast its message. In this new scenario, classical identification methods (such as fingerprints or face recognition) have been forcedly replaced by alternative biometric characteristics such as voice, as sometimes this is the only feature available. The present study benefits from the advances achieved during last years in understanding and modeling voice production. The paper hypothesizes that a gender-dependent characterization of speakers combined with the use of a set of features derived from the components, resulting from the deconstruction of the voice into its glottal source and vocal tract estimates, will enhance recognition rates when compared to classical approaches. A general description about the main hypothesis and the methodology followed to extract the gender-dependent extended biometric parameters is given. Experimental validation is carried out both on a highly controlled acoustic condition database, and on a mobile phone network recorded under non-controlled acoustic conditions.

No MeSH data available.