Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Biblos-e Archivo
Bachelor thesis . 2014
Data sources: Biblos-e Archivo
versions View all 2 versions
addClaim

Detección automática de voz degradada usando medidas de calidad

Authors: Cerame Lardies, Pedro;

Detección automática de voz degradada usando medidas de calidad

Abstract

En este proyecto se presenta el estudio e implementación de un sistema de detección de voz degradada haciendo uso de distintas medidas de calidad y, posteriormente, se evalúa el impacto de utilizar dichas medidas de calidad como parte del detector de actividad de voz de un sistema de reconocimiento de locutor. Al comienzo de este proyecto se hace uso de tres medidas de calidad distintas, ya analizadas en otros estudios, para obtener, mediante la combinación de dichas medidas, un único valor que permita, mediante un análisis previo, determinar la elegibilidad de una muestra de voz concreta. Finalizada la fase de desarrollo del sistema se realiza el experimento de combinar dichos valores con los utilizados por un detector de actividad de un sistema de reconocimiento de locutor desarrollado por el ATVS { Grupo de Reconocimiento Biométrico. Tras la realización de este proceso se evalúa el impacto que tienen las medidas de calidad estudiadas sobre el rendimiento total del sistema. Todos los experimentos se han probado sobre una base de datos proporcionada por el NIST { National Institute of Standards and Technology (NIST SRE 2012) utilizadas comúnmente en múltiples estudios del estado del arte. Por ultimo, se presentan las conclusiones y se proponen varias l neas de trabajo futuro.

In this work we present the study and implementation of a degraded voice detector making use of di erent quality measures. Also this work evaluates the impact of using these quality measures as part of a voice activity detector used on a speaker recognition system. At the beginning of this work we use three di erent quality measures, already analyzed in other studies, and obtaining, by the combination of these measures, one value that permits determinate the eligibility of a voice sample. When the developing phase is done, the quality measures are combined with the labels of a voice activity detector, developed by the ATVS group. After that, we evaluate the impact of these quality measures on the speaker recognition system. The database used for the experiments is the NIST SRE 2012. Finally the project conclusions are drawn and future lines of work are presented.

Country
Spain
Related Organizations
Keywords

Voz, Tratamiento automático de la, Telecomunicaciones

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green