This study aimed to develop a Voice Wellness Index (VWI) application combining the acoustic voice quality index (AVQI) and glottal function index (GFI) data and to evaluate its reliability in quantitative voice assessment and normal versus pathological voice differentiation. Cross-sectional study. A total of 135 adult participants (86 patients with voice disorders and 49 patients with normal voices) were included in this study. Five iOS and Android smartphones with the "Voice Wellness Index" app installed were used to estimate VWI. The VWI data obtained using smartphones were compared with VWI measurements computed from voice recordings collected from a reference studio microphone. The diagnostic efficacy of VWI in differentiating between normal and disordered voices was assessed using receiver operating characteristics (ROC). With a Cronbach's alpha of 0.972 and an ICC of 0.972 (0.964-0.979), the VWI scores of the individual smartphones demonstrated remarkable inter-smartphone agreement and reliability. The VWI data obtained from different smartphones and a studio microphone showed nearly perfect direct linear correlations (r = 0.993-0.998). Depending on the individual smartphone device used, the cutoff scores of VWI related to differentiating between normal and pathological voice groups were calculated as 5.6-6.0 with the best balance between sensitivity (94.10-95.15%) and specificity (93.68-95.72%), The diagnostic accuracy was excellent in all cases, with an area under the curve (AUC) of 0.970-0.974. The "Voice Wellness Index" application is an accurate and reliable tool for voice quality measurement and normal versus pathological voice screening and has considerable potential to be used by healthcare professionals and patients for voice assessment.
The purpose of this research was to develop an artificial intelligence-based method for evaluating substitution voicing (SV) and speech following laryngeal oncosurgery. Convolutional neural networks were used to analyze spoken audio sources. A Mel-frequency spectrogram was employed as input to the deep neural network architecture. The program was trained using a collection of 309 digitized speech recordings. The acoustic substitution voicing index (ASVI) model was elaborated using regression analysis. This model was then tested with speech samples that were unknown to the algorithm, and the results were compared to the auditory-perceptual SV evaluation provided by the medical professionals. A statistically significant, strong correlation with rs = 0.863 (p = 0.001) was observed between the ASVI and the SV evaluation performed by the trained laryngologists. The one-way ANOVA showed statistically significant ASVI differences in control, cordectomy, partial laryngectomy, and total laryngectomy patient groups (p < 0.001). The elaborated lightweight ASVI algorithm reached rapid response rates of 3.56 ms. The ASVI provides a fast and efficient option for SV and speech in patients after laryngeal oncosurgery. The ASVI results are comparable to the auditory-perceptual SV evaluation performed by medical professionals.
This study aimed to develop a multidimensional model for the evaluation of substitution voicing (SV) after laryngeal oncosurgery. The study group consisted of 121 adult male individuals: 59 patients with SV after laryngeal oncosurgery (endolaryngeal cordectomy, partial laryngectomy, total laryngectomy with tracheoesophageal prosthesis) and 62 healthy controls. A multidimensional protocol for the assessment of SV included, 1) self-reported speech evaluation with a short version of the Speech Handicap Index, 2) auditory-perceptual assessment, and 3) acoustic speech analysis using AMPEX® (Auditory Model Based Pitch Extractor) software. Moderate correlations were observed between parameters from self-reported auditory-perceptual and acoustic speech analysis domains. The multidimensional Substitution Voicing Index (SVI), including markers from these domains, was elaborated by using linear stepwise regression to determine the optimal set of parameters for categorising SV patients. The lowest mean SVI score was revealed in the control subgroup corresponding to the normal speech, followed by cordectomy subgroup and partial laryngectomy subgroup. The highest mean SVI score was revealed in the total laryngectomy subgroup, reflecting the most severely deteriorated quality of SV. One-way analysis of variance identified statistically significant differences between the mean SVI scores in separate subgroups. The results demonstrated the potential benefits of the SVI for a multidimensional evaluation of SV in patients after laryngeal oncosurgery.