Deep Learning for Voice Gender Identification: Proof-of-concept for Gender-Affirming Voice Care.

Journal: The Laryngoscope
PMID: 33219707

Abstract

OBJECTIVES/HYPOTHESIS: The need for gender-affirming voice care has been increasing in the transgender population in the last decade. Currently, objective treatment outcome measurements are lacking to assess the success of these interventions. This study uses neural network models to predict binary gender from short audio samples of "male" and "female" voices. This preliminary work is a proof-of-concept for further work to develop an AI-assisted treatment outcome measure for gender-affirming voice care.

Authors

  • Yael Bensoussan
    Morsani College of Medicine, University of South Florida, Tampa, FL, United States.
  • Jeremy Pinto
    Mila, Quebec Artificial Intelligence Institute, Montreal, Quebec, Canada.
  • Matthew Crowson
    Harvard Department of Otolaryngology - HNS, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, U.S.A.
  • Patrick R Walden
    Department of Communication Sciences and Disorders, St. John's University, Queens, New York, U.S.A.
  • Frank Rudzicz
    University of Toronto, Toronto, Canada.
  • Michael Johns
    Caruso Department of Otolaryngology - Head and Neck Surgery, University of Southern California, Los Angeles, California, U.S.A.

Keywords

External Resources

Popular Topics
Recent Journals