Likability of human voices: A feature analysis and a neural network regression approach to automatic likability estimation

Author

Eyben, Florian ; Weninger, Felix ; Marchi, Erik ; Schuller, Bjorn

Author_Institution

Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Munich, Germany

fYear

2013

fDate

3-5 July 2013

Firstpage

1

Lastpage

4

Abstract

Recently, the automatic analysis of likability of a voice has become popular. This work follows up on our original work in this field and provides an in-depth discussion of the matter and an analysis of the acoustic parameters. We investigate the automatic analysis of voice likability in a continuous label space with neural networks as regressors and discuss the relevance of acoustic features. We provide results on the Speaker Likability Database for comparison with previous work and a subset of the TIMIT database for validation.

Keywords

acoustic signal processing; feature extraction; neural nets; regression analysis; speaker recognition; speech processing; TIMIT database; acoustic features; acoustic parameters; automatic analysis; automatic likability estimation; continuous label space; feature analysis; human voices; neural network regression; speaker likability database; voice likability; Acoustics; Correlation; Databases; Speech; Standards; Superluminescent diodes; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis for Multimedia Interactive Services (WIAMIS), 2013 14th International Workshop on

Conference_Location

Paris

ISSN

2158-5873

Type

conf

DOI

10.1109/WIAMIS.2013.6616159

Filename

6616159