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/
UCrea
Master thesis . 2022
License: CC BY NC ND
Data sources: UCrea
versions View all 2 versions
addClaim

Métodos automáticos para la cuantificación de la calidad de la voz

Automatic methods for voice quality quantification
Authors: Fábrega Torrano, Julia;

Métodos automáticos para la cuantificación de la calidad de la voz

Abstract

El objetivo de este trabajo es estudiar la cuantificación de la calidad acústica de la voz mediante métodos automáticos, tanto en voz hablada como en canto, con el fin de evaluar la mejoría en la calidad de la voz después de un tratamiento experimental especifico. Para ello, se dispone de un dataset limitado de grabaciones de voces habladas y de canto, tanto de antes del experimento como de después, junto con una serie de etiquetas de valoraciones subjetivas proporcionadas por expertos. Después de estudiar varios métodos relacionados con el Acoustic Voice Quality Index, que es una métrica estandarizada para medir la calidad de una voz, el estudio se centra en métricas que cuantifican la presencia de armónicos y la calidad de vibratos. Los resultados del estudio indican que las valoraciones subjetivas de los expertos no se pueden modelar mediante técnicas automáticas, posiblemente debido a la gran variedad en etiquetas y el numero bajo de grabaciones. Tampoco se observa una mejoría en la calidad de la voz después del experimento según las métricas estudiadas.

The aim of this work is to study the quantification of the acoustic quality of the voice by means of automatic methods, both in spoken and singing voice, in order to evaluate the improvement in the acoustic quality of the voice after a specific experimental treatment. For this purpose, a limited dataset of spoken and singing voice recordings is available, both before the experiment and after, along with a series of subjective rating labels provided by experts. After studying various methods related to the Acoustic Voice Quality Index, which is a standardized metric for measuring voice quality, the study focuses on metrics that quantify he presence of harmonics and the quality of vibrates. The results of the study indicate that the subjective ratings of the experts cannot be modeled by automatic techniques, possibly due to the large variety in labels and the low number of recordings. There is also no improvement in voice quality after the experiment according to the metrics studied.

Máster en Ciencia de Datos

Country
Spain
Related Organizations
Keywords

Vibrato, Análisis acústico de la voz, AVQI, HNR, Calidad de la voz, Acoustic voice analysis, Voice quality

  • 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
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 91
    download downloads 89
  • 91
    views
    89
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
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!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
91
89
Green
Related to Research communities