Perceived Femininity in Singing Voice: Analysis and Prediction

2025-11-04

AI Summary

This study addresses the gap in voice gender perception research by systematically investigating Perceived Singing Voice Femininity (PSVF) — a previously unexplored dimension in singing. To this end, standardized acoustic stimuli were designed and subjective ratings collected from 128 participants, revealing significant inter-group differences in PSVF perception across demographic categories. Methodologically, we propose the first non-binary PSVF prediction model, built upon a fine-tuned x-vector framework that jointly leverages crowd-sourced subjective annotations and deep acoustic representations for multimodal PSVF quantification. Empirical evaluation demonstrates strong predictive performance (Pearson’s r = 0.79). The contribution includes: (1) the first publicly available, reproducible dataset of PSVF annotations; (2) a validated computational tool for automatic PSVF estimation; and (3) a theoretical framework enabling systematic analysis of gender stereotyping in musical content.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Natural Language Processing: Speech
• Application Domains: Humanities & Computational Social Science

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

This paper focuses on the often-overlooked aspect of perceived voice femininity in singing voices. While existing research has examined perceived voice femininity in speech, the same concept has not yet been studied in singing voice. The analysis of gender bias in music content could benefit from such study. To address this gap, we design a stimuli-based survey to measure perceived singing voice femininity (PSVF), and collect responses from 128 participants. Our analysis reveals intriguing insights into how PSVF varies across different demographic groups. Furthermore, we propose an automatic PSVF prediction model by fine-tuning an x-vector model, offering a novel tool for exploring gender stereotypes related to voices in music content analysis beyond binary sex classification. This study contributes to a deeper understanding of the complexities surrounding perceived femininity in singing voices by analyzing survey and proposes an automatic tool for future research.

Problem

• Analyzing perceived femininity in singing voices through participant surveys
• Developing automatic prediction model for singing voice femininity perception
• Exploring gender stereotypes in music beyond binary classification

Innovation

• Stimuli-based survey measures perceived singing voice femininity
• X-vector model fine-tuning enables automatic femininity prediction
• Tool analyzes gender stereotypes beyond binary classification