DeepAI AI Chat
Log In Sign Up

Voice Gender Scoring and Independent Acoustic Characterization of Perceived Masculinity and Femininity

by   Fuling Chen, et al.

Previous research has found that voices can provide reliable information for gender classification with a high level of accuracy. In social psychology, perceived vocal masculinity and femininity has often been considered as an important feature on social behaviours. While previous studies have characterised acoustic features that contributed to perceivers' judgements of speakers' vocal masculinity or femininity, there is limited research on building an objective masculinity/femininity scoring model and characterizing the independent acoustic factors that contribute to the judgements of speakers' vocal masculinity or femininity. In this work, we firstly propose an objective masculinity/femininity scoring system based on the Extreme Random Forest and then characterize the independent and meaningful acoustic factors contributing to perceivers' judgements by using a correlation matrix based hierarchical clustering method. The results show the objective masculinity/femininity ratings strongly correlated with the perceived masculinity/femininity ratings when we used an optimal speech duration of 7 seconds, with a correlation coefficient of up to .63 for females and .77 for males. 9 independent clusters of acoustic measures were generated from our modelling of femininity judgements for female voices and 8 clusters were found for masculinity judgements for male voices. The results revealed that, for both sexes, the F0 mean is the most critical acoustic measure affects the judgement of vocal masculinity and femininity. The F3 mean, F4 mean and VTL estimators are found to be highly inter-correlated and appeared in the same cluster, forming the second significant factor. Next, F1 mean, F2 mean and F0 standard deviation are independent factors that share similar importance. The voice perturbation measures, including HNR, jitter and shimmer, are of lesser importance.


page 5

page 9

page 14

page 17

page 24


Independent and automatic evaluation of acoustic-to-articulatory inversion models

Reconstruction of articulatory trajectories from the acoustic speech sig...

Automated Sex Classification of Children's Voices and Changes in Differentiating Factors with Age

Sex classification of children's voices allows for an investigation of t...

On incorporating social speaker characteristics in synthetic speech

In our previous work, we derived the acoustic features, that contribute ...

Acoustic Correlates of the Voice Qualifiers: A Survey

Our voices are as distinctive as our faces and fingerprints. There is a ...

Preliminary Study on SSCF-derived Polar Coordinate for ASR

The transition angles are defined to describe the vowel-to-vowel transit...

Common Phone: A Multilingual Dataset for Robust Acoustic Modelling

Current state of the art acoustic models can easily comprise more than 1...