Who Finds This Voice Attractive? A Large-Scale Experiment Using In-the-Wild Data

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Suda, Hitoshi, Watanabe, Aya, Takamichi, Shinnosuke
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910514721849344
author Suda, Hitoshi
Watanabe, Aya
Takamichi, Shinnosuke
author_facet Suda, Hitoshi
Watanabe, Aya
Takamichi, Shinnosuke
contents This paper introduces CocoNut-Humoresque, an open-source large-scale speech likability corpus that includes speech segments and their per-listener likability scores. Evaluating voice likability is essential to designing preferable voices for speech systems, such as dialogue or announcement systems. In this study, we let 885 listeners rate 1800 speech segments of a wide range of speakers regarding their likability. When constructing the corpus, we also collected the multiple speaker attributes: genders, ages, and favorite YouTube videos. Therefore, the corpus enables the large-scale statistical analysis of voice likability regarding both speaker and listener factors. This paper describes the construction methodology and preliminary data analysis to reveal the gender and age biases in voice likability. In addition, the relationship between the likability and two acoustic features, the fundamental frequencies and the x-vectors of given utterances, is also investigated.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04270
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Who Finds This Voice Attractive? A Large-Scale Experiment Using In-the-Wild Data
Suda, Hitoshi
Watanabe, Aya
Takamichi, Shinnosuke
Audio and Speech Processing
Sound
This paper introduces CocoNut-Humoresque, an open-source large-scale speech likability corpus that includes speech segments and their per-listener likability scores. Evaluating voice likability is essential to designing preferable voices for speech systems, such as dialogue or announcement systems. In this study, we let 885 listeners rate 1800 speech segments of a wide range of speakers regarding their likability. When constructing the corpus, we also collected the multiple speaker attributes: genders, ages, and favorite YouTube videos. Therefore, the corpus enables the large-scale statistical analysis of voice likability regarding both speaker and listener factors. This paper describes the construction methodology and preliminary data analysis to reveal the gender and age biases in voice likability. In addition, the relationship between the likability and two acoustic features, the fundamental frequencies and the x-vectors of given utterances, is also investigated.
title Who Finds This Voice Attractive? A Large-Scale Experiment Using In-the-Wild Data
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2407.04270