Voice Passing : a Non-Binary Voice Gender Prediction System for evaluating Transgender voice transition

TL;DR

This paper introduces a continuous voice femininity percentage system for transgender voice evaluation, utilizing a neural network model trained on French speakers, highlighting the influence of style, age, and gender perception.

Contribution

It presents a novel VFP system for transgender voice assessment and demonstrates the impact of training data and model architecture on prediction accuracy.

Findings

VFP system correlates well with perceptual evaluations

Model accuracy varies with speaker age and style

Training data and architecture significantly influence results

Abstract

This paper presents a software allowing to describe voices using a continuous Voice Femininity Percentage (VFP). This system is intended for transgender speakers during their voice transition and for voice therapists supporting them in this process. A corpus of 41 French cis- and transgender speakers was recorded. A perceptual evaluation allowed 57 participants to estimate the VFP for each voice. Binary gender classification models were trained on external gender-balanced data and used on overlapping windows to obtain average gender prediction estimates, which were calibrated to predict VFP and obtained higher accuracy than $F_0$ or vocal track length-based models. Training data speaking style and DNN architecture were shown to impact VFP estimation. Accuracy of the models was affected by speakers' age. This highlights the importance of style, age, and the conception of gender as binary or not, to build adequate statistical representations of cultural concepts.