A Comparison of an Artificial Intelligence Tool to Fundamental Frequency as an Outcome Measure in People Seeking a More Feminine Voice. (11th May 2021)
- Record Type:
- Journal Article
- Title:
- A Comparison of an Artificial Intelligence Tool to Fundamental Frequency as an Outcome Measure in People Seeking a More Feminine Voice. (11th May 2021)
- Main Title:
- A Comparison of an Artificial Intelligence Tool to Fundamental Frequency as an Outcome Measure in People Seeking a More Feminine Voice
- Authors:
- Bensoussan, Yael
Park, Christopher
Johns, Michael
Brown, Sarah
Pinto, Jeremy
Chang, Joseph
Courey, Mark - Abstract:
- Abstract : Objectives/Hypothesis: An artificial intelligence (AI) tool was developed using audio clips of cis‐male and cis‐female voices based on spectral analysis to assess %probability of a voice being perceived as female (%Prob♀). This program was validated with 92% accuracy in cisgender speakers. The aim of the study was to assess the relationship of f o on %Prob♀ by a validated AI tool in a cohort of trans females who underwent intervention to feminize their voice with behavioral modification and/or surgery. Study Design: Cohort study. Methods: Fundamental frequency ( f o ) from prolonged vowel sounds ( f o /a/) and f o from spontaneous speech ( f o ‐sp) were measured using the Kay Pentax Computerized Speech Lab (Montvale, NJ) in trans females postintervention. The same voice samples were analyzed by the AI tool for %Prob♀. Chi‐square analysis and regression models were performed accepting >50% Prob♀ as female voice. Results: Forty‐two patients were available for analysis after intervention. f o ‐sp post‐treatment was positively correlated with %Prob♀ ( R = 0.645 [ P < .001]). Chi‐square analysis showed a significant association between AI %Prob♀ >50% for the speech samples and f o ‐sp >160 Hz ( P < .01). Sixteen of 42 patients reached an f o ‐sp >160 Hz. Of these, the AI program only perceived nine patients as female (>50 %Prob♀). Conclusion: Patients with f o ‐sp >160 Hz after feminization treatments are not necessarily perceived as having a high probability ofAbstract : Objectives/Hypothesis: An artificial intelligence (AI) tool was developed using audio clips of cis‐male and cis‐female voices based on spectral analysis to assess %probability of a voice being perceived as female (%Prob♀). This program was validated with 92% accuracy in cisgender speakers. The aim of the study was to assess the relationship of f o on %Prob♀ by a validated AI tool in a cohort of trans females who underwent intervention to feminize their voice with behavioral modification and/or surgery. Study Design: Cohort study. Methods: Fundamental frequency ( f o ) from prolonged vowel sounds ( f o /a/) and f o from spontaneous speech ( f o ‐sp) were measured using the Kay Pentax Computerized Speech Lab (Montvale, NJ) in trans females postintervention. The same voice samples were analyzed by the AI tool for %Prob♀. Chi‐square analysis and regression models were performed accepting >50% Prob♀ as female voice. Results: Forty‐two patients were available for analysis after intervention. f o ‐sp post‐treatment was positively correlated with %Prob♀ ( R = 0.645 [ P < .001]). Chi‐square analysis showed a significant association between AI %Prob♀ >50% for the speech samples and f o ‐sp >160 Hz ( P < .01). Sixteen of 42 patients reached an f o ‐sp >160 Hz. Of these, the AI program only perceived nine patients as female (>50 %Prob♀). Conclusion: Patients with f o ‐sp >160 Hz after feminization treatments are not necessarily perceived as having a high probability of being female by a validated AI tool. AI may represent a useful outcome measurement tool for patients undergoing gender affirming voice care. Level of Evidence: 3 Laryngoscope, 131:2567–2571, 2021 … (more)
- Is Part Of:
- Laryngoscope. Volume 131:Number 11(2021)
- Journal:
- Laryngoscope
- Issue:
- Volume 131:Number 11(2021)
- Issue Display:
- Volume 131, Issue 11 (2021)
- Year:
- 2021
- Volume:
- 131
- Issue:
- 11
- Issue Sort Value:
- 2021-0131-0011-0000
- Page Start:
- 2567
- Page End:
- 2571
- Publication Date:
- 2021-05-11
- Subjects:
- Transgender females -- gender‐affirming voice care -- artificial intelligence -- voice‐gender recognition
Otolaryngology -- Periodicals
617.51005 - Journal URLs:
- http://onlinelibrary.wiley.com/journal/10.1002/(ISSN)1531-4995/issues ↗
http://www.interscience.wiley.com/jpages/0023-852X ↗
http://www.laryngoscope.com ↗
http://onlinelibrary.wiley.com/ ↗ - DOI:
- 10.1002/lary.29605 ↗
- Languages:
- English
- ISSNs:
- 0023-852X
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 5156.200000
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 19393.xml