Current Practices in Voice Data Collection and Limitations to Voice AI Research: A National Survey.

INTRODUCTION: Accuracy and validity of voice AI algorithms rely on substantial quality voice data. Although commensurable amounts of voice data are captured daily in voice centers across North America, there is no standardized protocol for acoustic data management, which limits the usability of these datasets for voice artificial intelligence (AI) research. OBJECTIVE: The aim was to capture current practices of voice data collection, storage, analysis, and perceived limitations to collaborative voice research. METHODS: A 30-question online survey was developed with expert guidance from the voicecollab.ai members, an international collaborative of voice AI researchers. The survey was disseminated via REDCap to an estimated 200 practitioners at North American voice centers. Survey questions assessed respondents' current practices in terms of acoustic data collection, storage, and retrieval as well as limitations to collaborative voice research. RESULTS: Seventy-two respondents completed the survey of which 81.7% were laryngologists and 18.3% were speech language pathologists (SLPs). Eighteen percent of respondents reported seeing 40%-60% and 55% reported seeing >60 patients with voice disorders weekly (conservative estimate of over 4000 patients/week). Only 28% of respondents reported utilizing standardized protocols for collection and storage of acoustic data. Although, 87% of respondents conduct voice research, only 38% of respondents report doing so on a multi-institutional level. Perceived limitations to conducting collaborative voice research include lack of standardized methodology for collection (30%) and lack of human resources to prepare and label voice data adequately (55%). CONCLUSION: To conduct large-scale multi-institutional voice research with AI, there is a pertinent need for standardization of acoustic data management, as well as an infrastructure for secure and efficient data sharing. LEVEL OF EVIDENCE: 5 Laryngoscope, 134:1333-1339, 2024.

Validation of an AI-assisted Treatment Outcome Measure for Gender-Affirming Voice Care: Comparing AI Accuracy to Listener's Perception of Voice Femininity.

OBJECTIVES: There is currently a lack of objective treatment outcome measures for transgender individuals undergoing gender-affirming voice care. Recently, Bensoussan et al developed an AI model that is able to generate a voice femininity rating based on a short voice sample provided through a smartphone application. The purpose of this study was to examine the feasibility of using this model as a treatment outcome measure by comparing its performance to human listeners. Additionally, we examined the effect of two different training datasets on the model's accuracy and performance when presented with external data. METHODS: 100 voice recordings from 50 cisgender males and 50 cisgender females were retrospectively collected from patients presenting at a university voice clinic for reasons other than dysphonia. The recordings were evaluated by expert and naïve human listeners, who rated each voice based on how sure they were the voice belonged to a female speaker (% voice femininity [R]). Human ratings were compared to ratings generated by (1) the AI model trained on a high-quality low-quantity dataset (voices from the Perceptual Voice Quality Database) (PVQD model), and (2) the AI model trained on a low-quality high-quantity dataset (voices from the Mozilla Common Voice database) (Mozilla model). Ambiguity scores were calculated as the absolute value of the difference between the rating and certainty (0 or 100%). RESULTS: Both expert and naïve listeners achieved 100% accuracy in identifying voice gender based on a binary classification (female >50% voice femininity [R]). In comparison, the Mozilla-trained model achieved 92% accuracy and the previously published PVQD model achieved 84% accuracy in determining voice gender (female >50% AI voice femininity). While both AI models correlated with human ratings, the Mozilla-trained model showed a stronger correlation as well as lower overall rating ambiguity than the PVQD-trained model. The Mozilla model also appeared to handle pitch information in a similar way to human raters. CONCLUSIONS: The AI model predicted voice gender with high accuracy when compared to human listeners and has potential as a useful outcome measure for transgender individuals receiving gender-affirming voice training. The Mozilla-trained model performed better than the PVQD-trained model, indicating that for binary classification tasks, the quantity of data may influence accuracy more than the quality of the data used for training the voice AI models.

A Comparison of an Artificial Intelligence Tool to Fundamental Frequency as an Outcome Measure in People Seeking a More Feminine Voice.

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 fo 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 (fo ) from prolonged vowel sounds (fo /a/) and fo from spontaneous speech (fo -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. fo -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 fo -sp >160 Hz (P < .01). Sixteen of 42 patients reached an fo -sp >160 Hz. Of these, the AI program only perceived nine patients as female (>50 %Prob♀). CONCLUSION: Patients with fo -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.

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

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. STUDY DESIGN: Retrospective cohort study. METHODS: Two hundred seventy-eight voices from male and female speakers from the Perceptual Voice Qualities Database were used to train a deep neural network to classify voices as male or female. Each audio sample was mapped to the frequency domain using Mel spectrograms. To optimize model performance, we performed 10-fold cross validation of the entire dataset. The dataset was split into 80% training, 10% validation, and 10% test. RESULTS: Overall accuracy of 92% was obtained, both when considering the accuracy per spectrum and per patient metric. The accuracy of the model was higher for recognizing female voices (F1 score of 0.94) compared to male voices (F1 score of 0.87). CONCLUSIONS: This proof of concept study shows promising performance for further development of an AI-assisted tool to provide objective treatment outcome measurements for gender affirming voice care. LEVEL OF EVIDENCE: 3 Laryngoscope, 131:E1611-E1615, 2021.