CO2 Transoral laser microsurgery (TLM) is a preferred technique for early-stage glottic lesions [1] (Yin et al Auris Nasus Larynx 50(3):415-422, 1), but reconstruction of the anterior commissure remains an unresolved issue. The anterior commissure is a surgically challenging area due to limited accessibility, high incidence of postoperative stenosis and risk of recurrence [2] (Chone et al Arch Otolaryngol Head Neck Surg 133(9):882-887, 2). To share our experience with a single-stage reconstruction technique for anterior commissure defects following TLM, using a buccal mucosal graft secured with sutures and tissue glue, and to present post-surgical outcomes. A series of five cases performed at VPS Lakeshore Hospital, Kochi, over a 1.5-year period (January 2024-April 2025) in patients with squamous cell carcinoma or carcinoma in situ of anterior commissure of glottis following TLM were evaluated. Written informed consent was obtained from all patients. TLM was performed using carbon dioxide laser, followed by reconstruction using a buccal mucosal graft fixed with polypropylene sutures and tissue glue. Outcomes were assessed using Voice Handicap Index (VHI) scores (Johnson et al Am J Speech-Language Pathol 6: 66-70, 3), video laryngoscopic evaluation of graft integrity, and rates of postoperative stenosis or adhesion. All patients remained free of disease at the end of the follow up period. VHI scores indicated acceptable postoperative voice quality. Post operative healing in patients who underwent transcutaneous suture fixation of grafts with tissue glue support demonstrated better and predictable outcomes in terms of stable graft positioning, good vocal cord approximation and minimal fibrosis. This novel, single-stage reconstruction technique allows good healing of anterior commissure defects by preventing stenosis. Functional outcomes measured by VHI are good. It offers a cost-effective alternative to staged procedures while ensuring optimal vocal outcomes.

The human voice has various distinct characteristics that are referred to as voiceprint. The frequency employed in forensic phonetics to highlight the crime is called a voiceprint. Give us a dependable piece of evidence that can be utilized to determine guilt or identify a perpetrator. There are statistical and mathematical methodologies available, as well as artificial intelligence menthid. On the sound, a visual and auditory analysis is done, and then an assessment is produced using several criteria. Speaker identification algorithms have a success rate of 85 percent to 99 percent. Misrecognition occurs at a rate of 3%, whereas non-recognition occurs at a rate of 10%. In forensic voice comparison, there is a growing emphasis on combining automated and phonetic approaches to increase the validity and reliability of speech evidence presented to courts. To analyze the degree to which long-term measurements of the speech signal collect complementing speaker-specific information, we give a comparison of them. The best-performing system's output was utilized to assess the value of auditory-based voice quality analysis of subpharyngeal (filter) and laryngeal (source) voice quality in system testing. The results imply that the (semi-)automatic system's problematic speakers may be predicted to some degree based on their subpharyngeal voice quality profiles, with the least distinctive speakers giving the weakest evidence and the most misclassifications. The misclassified couples, on the other hand, were readily distinguished using aural analysis. Thus, the quality of the laryngeal voice may be valuable in resolving problematic pairings for (semi-)automatic systems, thus boosting their overall performance.

Background/Objectives: The aim of this study was to assess the short-term and long-term effectiveness of group voice therapy in changing vocal behaviour and improving voice quality (VQ) among teachers with hyperfunctional voice disorders (HFVD), using both subjective and objective measures. Methods: Thirty-one teachers participated in a structured group voice therapy programme. Participants underwent videoendostroboscopic evaluation of laryngeal morphology and function, perceptual assessment of voice, acoustic analysis of voice samples, and aerodynamic measurements of phonation. Patients’ self-assessment of VQ and its impact on quality of life were measured using a Visual Analogue Scale (VAS) and the Voice Handicap Index-30 (VHI-30). Evaluations were conducted at four time points: pre-therapy (T0), immediately post-therapy (T1), and at 3-month (T3) and 12-month (T12) follow-up visits. Results: Significant improvement was observed between T0 and T1 in perceptual voice evaluations: grade, roughness, asthenia, strain, loudness, fast speaking rate, as well as in neck muscle tension, shimmer, patients’ most harmful vocal behaviours, VHI-30 scores, patients VQ evaluation, and its impact on quality of life (all p < 0.05). Almost all parameters of subjective and objective voice assessment improved over the 12-month observation period, with the greatest improvement between T0 and T12 (all p < 0.05), indicating lasting reduced laryngeal tension and improved phonatory efficiency. Conclusions: Group voice therapy has been shown to be an effective treatment for teachers with HFVD, leading to significant and long-lasting improvements in perceptual, acoustic, and self-assessment outcomes. Therapy also promoted healthier vocal and lifestyle behaviours, supporting its role as a successful and cost-effective rehabilitation and prevention method for occupational voice disorders.

BackgroundHeart failure (HF) is a common chronic disease that contains the risk decompensation. Most remote HF monitoring relies on symptoms and basic vitals, which signal trouble only when having symptoms of decompensation, failing to prevent hospitalization in half of the cases. Recent evidence suggests that voice alterations may predict clinical worsening, offering a novel and non-invasive biomarker.ObjectiveThis prospective study aims to validate AI-based voice analysis software for detecting heart failure deterioration after hospital discharge. Primary objective is to estimate the software’s sensitivity in predicting HF events. Secondary objectives include assessing patient adherence and usability of the app, and exploring associations between voice features and blood biomarkers.MethodsWe are conducting a multicentre, prospective observational study including 123 patients hospitalized for acute decompensated heart failure. Patients are enrolled within three days of admission to the cardiology ward, irrespective of HF subtype. As of mid-June 2025, 60 patients have been enrolled, yielding over 14,000 voice recordings. During hospitalisation, participants record daily voice samples while clinically volume overloaded. The final recording prior to discharge, once recompensation is achieved, serves as the individualised baseline (=reference) of the voice pattern. Participants continue daily voice recordings and structured health questionnaires after discharge for a six-month follow-up period, with evaluations at months 1, 3 and 6. Voice recordings consist of 3 vowels and 2 pre-defined sentences. All data are transmitted to a secure cloud infrastructure, where AI-based voice analysis is performed. If symptom thresholds are exceeded, health care professionals (HCP) receive alerts about the potential risk for HF-related decompensation. HCPs may adjust therapy upon their own discretion. Voice-based predictions will be analysed retrospectively. Outcomes are based on HF deterioration events, which was defined as mortality, HF related hospitalisation and intensifying HF therapy due to worsening of HF. Additionally, blood samples collected at baseline, 3, and 6 months will be used to explore the relationship between voice characteristics and conventional or novel blood biomarkers.Conclusionsrelevance The Pre-DETECT HF study explores whether a vocal biomarker could be used as a predictor for HF deterioration. If successful, this approach could enhance remote heart failure monitoring and allow for more timely intervention in patients with HF.

BackgroundHeart failure (HF) remains a major global health burden, affecting over 64 million individuals worldwide. Accurate assessment of HF severity is pivotal for clinical management but typically relies on resource-intensive methods such as imaging and laboratory biomarkers. Voice analysis represents a novel, scalable, and non-invasive approach to monitor physiological changes linked to HF severity.PurposeThis study aims to develop and validate an artificial intelligence (AI)-based voice analysis model to predict HF severity in patients undergoing treatment and in control subjects.MethodsThis prospective clinical study is being conducted across multiple academic hospitals. We will recruit HF patients receiving treatment and matched control subjects without HF. Voice recordings will be collected at multiple time points: at discharge, and at 1, 5, and 13 weeks post-discharge. Simultaneously, clinical data including NT-proBNP levels, NYHA functional class, dyspnea scale scores, and echocardiographic findings will be gathered. An AI model will be trained on extracted acoustic features and clinical variables to classify HF severity into four categories: normal, mild, moderate, and severe.ResultsWe hypothesize that changes in voice characteristics will reflect dynamic shifts in pulmonary and systemic congestion, correlating with traditional HF severity markers. The AI model’s performance will be evaluated using standard metrics including area under the curve (AUC), sensitivity, and specificity, and compared against established clinical benchmarks.ConclusionThis study is expected to demonstrate the feasibility of voice-based AI tools for non-invasive monitoring of HF severity. Such technology may enable continuous, remote assessment of patients, enhancing clinical decision-making and patient management in heart failure care.

Single vocal cord irradiation (SVCI) vs whole laryngeal radiotherapy in the treatment of T1aN0 glottic cancer A prospective randomized trial.

Mental effort is theoretically and qualitatively known to increase when individuals intentionally alter their voice quality, as they learn to do in voice therapy or voice training. The purpose of this study was to examine the effect of voice quality alteration on mental effort using both (objective) cognitive pupillometry methods and (subjective) self-report scales, as well as to examine the association between these two measurement approaches. In a within-participant repeated-measures design, the intentional production of three voice qualities-fry, breathy, and twang-was compared to habitual voice production for its effect on pupil dilation and on the Borg Category Ratio-10 Mental Effort Scale and the National Aeronautics and Space Administration Task Load Index Mental Effort subscale. For all three intentionally altered voices-fry, breathy, and twang-pupil dilation and perceived self-report yielded significant positive effects with very large effect sizes. The association between pupil dilation in millimeter and self-report scale values was significant, moderate, and positive. Exploratory investigation also suggested that twang and breathy voices were more demanding than fry, and that a baseline subtraction was more meaningful and powerful approach to baseline correction than baseline division. As hypothesized, intentional voice quality change yields both significant increases in pupil dilation and perceived mental effort. These measures were moderately associated. Findings are fundamental to clinical and artistic endeavors requiring intentional voice quality change.

The Effectiveness of Eclectic Voice Therapy on Multidimensional Voice Parameters in Patients with Primary Muscle Tension Dysphonia.

The nasal and paranasal cavities constitute integral components of the vocal tract resonator system, yet their precise contribution to voice quality remains a subject of debate. While early anatomical and acoustic models (1-3) suggested that sinus coupling through open ostia may introduce anti-resonances and spectral alterations, subsequent investigations employing cadaveric dissections, physical simulations, and three-dimensional replicas (4, 5) have confirmed notable effects on frequency response and formant balance. Clinical studies, including those examining patients with chronic rhinosinusitis undergoing functional endoscopic sinus surgery (FESS), have shown that surgical management can improve both sinonasal and vocal quality of life without adverse effects on voice characteristics (6,7). However, conventional acoustic measures such as jitter and shimmer frequently fail to detect such changes (8). In contrast, Mel-frequency cepstral coefficients (MFCCs), which transform the speech spectrum into a perceptually weighted domain, have shown superior sensitivity to resonance-related shifts and hypernasality (9). Based on this evidence, we investigated whether MFCCs and spectral flatness can more accurately identify post-operative alterations in resonance that are not captured by traditional acoustic parameters.

Normative Electroglottographic Voice Measures in Adult Greek Speakers: Effects of Age and Gender on Fundamental Frequency and Jitter.

Perceiving Physiology from the Voice: Evidence for Physiological Coupling Between Laryngeal and Epilaryngeal Adjustments.

Effects of STN-DBS treatment on voice characteristics in patients with Parkinson's Disease

Acoustic and Perceptual Comparison of the Immediate Effects of Semi-Occluded Vocal Tract Exercises and Vocal Facilitating Techniques on the Vocal Function of Traditional Iranian Singers With Muscle Tension Dysphonia: A Randomized Clinical Trial.

Investigation of the Relationship Between Laryngopharyngeal Reflux and the Body Roundness Index.

Objectives: This study aimed to compare voice measurements between children with cleft palate (CP) based on the presence of compensatory articulation (CA), to examine the correlations among acoustic, perceptual, and nasalance scores, and to investigate differences in acoustic measures across vowel contexts. Methods: The study was conducted retrospectively on 22 children aged 4-5 years: 14 children with CP exhibiting CA and 8 children with CP not exhibiting CA. Acoustic measurements, including cepstral peak prominence (CPP), L/H spectral ratio (SR), mean fundamental frequency (F0), F0 range in semitones, and nasalance scores were analyzed, and the GRBAS scale was evaluated. Results: Children with CP exhibiting CA showed significantly higher SR<sub>max</sub>, Mean F0, and nasalance scores; and were perceptually rated higher in the Grade and Rough. Correlations among the measurements revealed that nasalance scores were positively correlated with Grade and Roughness. Breathiness was positively correlated with Grade, Roughness, and mean F0, and SR showed a negative correlation with Breathy and Mean F0. Acoustic measurements for CPP and SR were highest in the low vowel context, followed by the mixed vowel context and the high vowel context. Conclusion: This study suggests that reduced voice quality was perceived in children with CA, and some acoustic measures reflected its characteristics. However, acoustic analysis alone was limited in examining the voice quality of children with CP, emphasizing the need for multidimensional evaluation that considers vowel contexts.

IntroductionObstructive sleep apnea (OSA) involves recurrent upper airway obstructions during sleep, leading to fragmentation and oxygen desaturation. Vocal complaints and orofacial myofunctional changes are common, but few studies assess both aspects in diagnosed patients.ObjectiveTo assess vocal parameters and orofacial myofunctional conditions in adults diagnosed with OSA, comparing them to a control group at low risk for OSA.MethodsCross-sectional study. A convenience sample (N = 63) was included: 33 with OSA confirmed by polysomnography and 30 controls at low risk for OSA (STOP-BANG < 3 and no reported snoring in Stanford Snoring Scale), aged between 18–60 years. Assessments included perceptual-auditory analysis of voice quality (GRBASI scale, Vocal Symptom Scale (VSS), maximum phonation time (MPT) for vowels and s/z ratio) and orofacial myofunctional evaluation (OMES-E protocol). Participants who had received previous treatment or medical conditions affecting OSA, voice or orofacial function were excluded.ResultsOSA group showed significantly higher scores on VSS and lower scores on OMES-E protocol. They also displayed shorter MPT, worse performance in s/z ratio, reduced pneumophonoarticulatory coordination, and higher frequency of vocal alterations. The OSA group revealed mean apnea-hypopnea index of 45.80, indicates predominance of severe cases, as well as increased desaturation index.ConclusionIndividuals with OSA exhibit impairments in both orofacial myofunctional and vocal parameters, with negative alterations observed in MPT speech rate, pneumophonoarticulatory coordination, and s/z ratio compared with subjects with no OSA complaints. These findings highlight the importance of evaluating vocal and orofacial aspects together in OSA.

This 24-month longitudinal study involving isolated rapid eye movement sleep behavior disorder (iRBD), early-stage Parkinson's disease (PD), and matched healthy control subjects aimed to assess whether acoustic speech features from real-world smartphone calls provide passive progressive biomarkers in synucleinopathies. Participants underwent clinical assessments at baseline, 1, and 2 years. Speech was continuously captured during phone calls via a standardized smartphone application, segmented, and analyzed for speech impairment severity end points and key acoustic features of monopitch, vowel articulation, voice quality, and articulation rate. We used linear mixed-effect modeling to estimate speech progression and calculated sample size requirements to demonstrate slowing of progression under anticipated treatment effects. Over 31,000 phone calls (>1,000 hours) were collected from 71 participants including those with iRBD, PD, and healthy controls. Compared with controls, both individuals with iRBD and PD showed significant declines in speech impairment severity end points based on spectral changes and artificial intelligence-based neural embeddings. The subjects with iRBD also exhibited declines in vowel articulation and articulation rate. For a 2-year neuroprotective trial aiming for 50% drug efficacy, the most efficient sample size estimate based on time-to-event analysis was 74 iRBD and 84 PD participants per arm using the neural embedding end point. The phone call analysis requiring no patient effort or clinical supervision can detect speech decline in prodromal and early synucleinopathies, providing a potential paradigm shift for clinical trial design and neuroprotective intervention end points. ANN NEUROL 2025.

Considering differences in voice features, speech overlapping, and continuous audio streams, speaker identification in multi-speaker audio settings is still a difficult issue. This paper introduces a speaker identification method that uses Mel-Frequency Cepstral Coefficients (MFCCs) and Delta-MFCCs to extract robust features from non-overlapping multi-speaker audio. Feature matching is done using a Log-Likelihood-based decision mechanism, whereas speaker modelling and training are done using Gaussian Mixture Models (GMMs). The integration of Voice Activity Detection (VAD) allows for the effective processing of continuous recordings by separating speech from non-speech sections. A custom dataset with 89 speakers, each giving five utterances of 20-30 seconds, and the VoxForge speech corpus are used to train the system. One hundred test samples per category are used for performance evaluation utilising two- to five-speaker audio mixes. The identification accuracy for two-speaker audio is 92%, three-speaker audio is 84%, four-speaker audio is 72%, and five-speaker audio is 66%, according to the suggested method. As the number of speakers rises, the system's effectiveness steadily declines, although it works well for scenarios with fewer speakers. In conclusion, the proposed framework provides an effective and encouraging approach to speaker identification in continuous audio streams and multi-speaker settings where the speakers do not overlap.

To evaluate the effect of allergic rhinitis and its severity on voice quality in a multidimensional manner. Sixty-six adults with allergic rhinitis and fourty five normophonic adults without allergic rhinitis were included in the study. Medical history, skin prick test, endoscopic nasal examination, Total Nasal Symptom Score (TNSS), laryngeal imaging, Acoustic Voice Quality Index (AVQI), Cepstral Peak Prominence Smoothed (CPPS), aerodynamic measurements (/a/,/s/,/z/ and s/z ratio), Voice Handicap Index-10 (VHI-10), Vocal Tract Discomfort Scale (VTD), Vocal Fatigue Index (VFI), Reflux Finding Score (RFS), Reflux Symptom Index (RSI), and auditory perceptual assessment (GRBAS) tools were used for evaluation. Allergic rhinitis is associated with adverse effects on the vocal tract, with discomfort increasing as the severity of rhinitis worsens. Voice-protective practices appear important to minimize the risk of dysphonia in patients with allergic rhinitis.

Background/Objectives: Speech and motor control share overlapping neural mechanisms, yet their quantitative relationships in Parkinson’s disease (PD) remain underexplored. This study investigated bidirectional associations between acoustic voice features and objective motor metrics to better understand how vocal and motor systems relate in PD. Methods: Cross-sectional baseline data from participants in a randomized neuromodulation trial were analyzed (n = 13). Motor performance was captured using an Integrated Motion Analysis Suite (IMAS), which enabled quantitative, objective characterization of motor performance during balance, gait, and upper- and lower-limb tasks. Acoustic analyses included harmonic-to-noise ratio (HNR), smoothed cepstral peak prominence (CPPS), jitter, shimmer, median fundamental frequency (F0), F0 standard deviation (SD F0), and voice intensity. Univariate linear regressions were conducted in both directions (voice ↔ motor), as well as partial correlations controlling for PD motor symptom severity. Results: When modeling voice outcomes, faster motor performance and shorter movement durations were associated with acoustically clearer voice features (e.g., higher elbow flexion-extension peak speed with higher voice HNR, β = 8.5, R2 = 0.56, p = 0.01). Similarly, when modeling motor outcomes, clearer voice measures were linked with faster movement speed and shorter movement durations (e.g., higher voice HNR with higher peak movement speed in elbow flexion/extension, β = 0.07, R2 = 0.56, p = 0.01). Conclusions: Voice and motor measures in PD showed significant bidirectional associations, suggesting shared sensorimotor control. These exploratory findings, while limited by sample size, support the feasibility of integrated multimodal assessment for future longitudinal studies.