Science AI Journal
Medicine · Research topic

Open research questions in Voice and Speech Disorders

67 unresolved questions extracted from the limitations and future-work sections of 1,454 Voice and Speech Disorders papers in our library. Each links back to the study that raised it.

What the literature leaves open

  • Although the speech production aspects of dysarthria in PD have been well studied, little is known about how people with PD perceive dysarthric speech.

    Perceptual Training for People With Parkinson's Disease · 2026 · DOI

  • Future research should focus on improving personalized DSR on spontaneous speech and longer utterances in the case of read speech, with a specific focus on particular phonemes.

    Comparing Human and Automatic Recognition of Dutch Dysarthric Continuous Speech: A Case Study · 2026

  •  Can be done in different populations  Can be done more sample size www.wjahr.com │ Volume 10, Issue 7, 2026 │ ISO 9001:2015 Certified Journal │ 100 Shahanas et al. World Journal of Advance Healthcare Research REFERENCE 1. Ahmed, M., Aly, H., Ahmed, S., & Gelaney, M. (2026). Acoustic voice characteristics of Arabicspeaking dysphonic adults using PRAAT software. Journal of Voice. Advance online publication. 2. AlBustan, S. A., Marie, B. S., Darawsheh, W. B., & Natour, Y. S. (2022). Voice handicap and acoustic measures among Arab Kuwaiti prospective professional singers. Journal of Voice. Advance online publication. 3. Aswathy, K., & Shetty, S. Acoustic characteristics of voice among male khatibs using PRAAT software. International Journal of Health Sciences, 2022; 6(S4): 11234–11241. 4. Büyükatalay, Z., Gökmen, Z., & Dursun, G. Comparison of voice disorder risk between teachers and Islamic religious officials. Journal of Voice, 2020; 34(5): 812.e1–812.e7. 5. Colton, R. H., & Casper, J. K. Understanding voice problems: A physiological perspective for diagnosis and treatment (3rd ed.). Williams & Wilkins, 1996. 6. Elsherbeny, M., Baz, H., & Afsah, O. Acoustic characteristics of voice and speech in Arabicspeaking children with stuttering. Folia Phoniatrica et Logopaedica, 2022; 74(4): 256–264. 7. Farahat, M., & Mesallam, T. A. Psychosocial assessment of voice problems among Saudi in Medicine and imams.

    ACOUSTIC ANALYSIS OF VOICE IN MU'ADHIN AND KHATIB · 2026 · DOI

  • In summary, SSIs are a rapidly growing technology that provides a natural and intuitive spoken communication interface without audible speech. By examining diverse bio-integrated systems, from skin-mounted and oral sensors to implanted neural devices, this review highlights the trade-offs among portability, invasiveness, signal fidelity, and robustness. Continued innovation in functional materials, sensing modalities, and signal processing is essential to developing long-term, accurate, and socially acceptable solutions for communication in both clinical and daily settings. The development of future bio-integrated hardware for SSIs presents distinct challenges and opportunities that must be addressed separately for each system type, as each operates under different constraints and applications. Epidermal systems represent the most promising avenue for widespread adoption in daily settings due to their non-invasive nature. Two key challenges remain: long-term comfort and social acceptance. Among epidermal approaches, EMG systems, one of the most promising sensing modalities for Page 42 of 55 Dong et al. Soft Sci. 2026, 6, 54 SSIs, require high-density electrode arrays to ensure adequate data for recognition. However, integrating these arrays into a single, relatively large patch may introduce discomfort and skin irritation over extended periods due to the large skin area covered. Future work should focus on developing gas-permeable and biocompatible sensors[73,281] that allow the patch to conform to the skin while remaining breathable and unobtrusive during long-term wear. Furthermore, to improve social acceptance, the development of transparent and thin electrodes should be prioritized, particularly for facial movement sensing. Recent studies highlight this aesthetic barrier, indicating that users frequently reject highly visible facial wearables due to social stigma and discomfort. Consequently, making devices truly invisible is just as critical as ensuring their functionality. Integrating sensors into daily wear or utilizing transparent and compliant materials is essential for widespread adoption and user comfort. For IMUs, despite their high efficiency in capturing three-axis motions, further improvements are needed to enhance sensitivity to subtle facial or jaw movements. This may be achieved by minimizing the size of circuit boards or by transitioning to circuit boards employing soft substrates that conform better to the skin surface. Placing sensors in socially acceptable and low-visibility regions is also crucial for improving user acceptance. Strain sensors, while useful for capturing skin deformations, face integration challenges. Increasing their channel density and integrating multiple sensors into a single patch without adding bulk represents a promising research direction.

    Bio-integrated systems for silent speech recognition: from advanced bioplatforms to machine learning-assisted biosignal decoding · 2026 · DOI

  • The Root-Guided Random Forest Feature Selection (RGRFFS) algorithm for speech- based Parkinson's disease recognition is discussed in this paper. In this method, the feature selection process used acoustic and spectral speech parameters to discover biomarkers linked to Parkinsonian speech. Through ranking the features based on their Root Importance Score (RIS), the most discriminating attributes were selected without loss of classification performance and with reduction of redundant features. The findings suggest that Root-Guided feature selection technique enables an efficient feature selection method for discriminative acoustic biomarkers in PD classification. It was found out that the framework is able to achieve accuracy of 93.85%, with precision, recall, and F1 score equal to 0.94, demonstrating its ability to discriminate between speech of patients with PD and normal speech with high reliability. The research shows the efficiency of the feature selection technique in terms of improvement of classification performance and disease discrimination. Future work may include the use of large and varied speech data sets for enhanced performance and generalization. In addition, deep learning algorithms and multimodal biomarkers may be investigated for use in real-time screening of Parkinson's disease.

    A Root-Guided Random Forest Framework with Discriminative Voice Biomarker Selection for Parkinson’s Disease Detection · 2026 · DOI

  • Additional studies on micro-gestural expression in performance further support the idea that small sonic details can carry significant expressive weight (Windsor, 2011; Leman, 2016).

    Snoring as Involuntary Vocalisation: Mapping Its Rhythmic, Timbre-Based, and Affective Qualities in Experimental Music Composition · 2026 · DOI

  • As a single-subject case report without a control group, these findings are not conclusive. There was also a potential for bias as the clinician was the sole evaluator and the client’s perceived expectations of benefit could have influenced his performance (i.e., subject bias). ing hypertonicity in the vocal system without direct laryngeal manipulation, or vocal exercises/training, vocal function improved for a client with symptoms of behavioral dysphonia. Despite variability, immediately following most sessions, jaw movement, phonation time, breath flow, loudness, and jitter improved. By the final session, loudness increased by 6 dB and vocal range increased by six whole tones. During functional singing, breath fluency, HNR, and vocal range had all improved following the treatment course. This report adds to the limited number of studies merging the practices of professional massage therapy and clinical voice care. Although the human voice is a whole-body phenomenon, future controlled research should identify specific mechanisms, targets, and methods for optimal release of vocal restriction while taking the whole body into account. It is hoped that such investigations continue to inspire interdisciplinary collaboration, harmonizing the clinical knowledge and expertise of voice care professionals with the therapeutic insight and skilled touch of licensed massage therapists. As the evidence base in this area of research continues to grow, the clinical value that licensed massage therapists offer to the voice care team may be increasingly recognized in professional practice. In such a paradigm, specially trained massage therapists can assess the whole body and release physical restriction affecting the vocal system at baseline, helping voice pathologists and their patients proceed to voice therapy with less physical obstacles in their way. ACKNOWLEDGMENTS I wa n t to t h a n k my m e n to r N i n a Kottcamp, LMT, for her kind support, thoughtful guidance, and selfless encouragement. I am thankful to Chris Purcell for connecting me with a person in need. I want to thank Barb Stockland, for her valuable research support. And to my Lord and Savior Jesus Christ, who set me on this path to help and guide others to heal.

    Massage Therapy for a Voice Student with Behavioral Dysphonia When Singing: A Case Report · 2026 · DOI

  • and for Lack of Model Interpretability: A limitation of the proposed system is the limited interpretability of the trained model. Future work can address this by incorporating Explainable AI (XAI) techniques, such as feature attribution methods, to provide insight into how input features influence model predictions. through Operating on Simulated Data: The current implementation relies on simulated patient input provided files. Future development may involve integrating real-time data sources, such as wearable sensors or Internet of Things (IoT) devices, to better capture real-world variability. static CSV VI FUTURE ENHANCEMENTS Further improvements are required to extend the proposed system beyond its current implementation and evaluate its suitability for real-world clinical use. Expanding the Dataset: Future work will involve using larger and more diverse datasets to improve model robustness and generalizability. Improving Model Interpretability: Future work may incorporate Explainable AI (XAI) techniques to improve understanding of how input features influence model predictions. Real-World Evaluation: Future work may involve evaluating the system using real-world clinical data and deployment scenarios, including data obtained from wearable or IoT-based devices. symptoms.

    Parkinson's Disease Prediction Using ML · 2026 · DOI

  • Non-classical singing is generally considered detrimental to vocal health and thus the information on challenges contemporary commercial singers (CCS) pose to otolaryngologists and other healthcare professionals is scarce.

    Considerations and demands in the voice care of contemporary commercial singers in occupational health and safety aspects · 2022 · DOI

  • Little is known regarding the incidence of voice problems in student actors and the methods used to train the speaking voice in Master of Fine Arts (MFA) acting programs.

    Voice Training Methods in MFA Acting Programs · 2018 · DOI

  • 14 Many athletes, and singers as well, fear that a reduction in practice time or volume will result in a loss of muscle strength, overall conditioning, and performance abilities; however, no studies have found such a pattern.

    Effect of a Tapered Rehearsal Schedule on Voice in Choir Singers · 2017

  • Paradoxical vocal cord motion (PVCM), also termed vocal cord dysfunction, is a poorly understood disorder of episodic dyspnea characterized by inappropriate vocal cord adduction during inspiration and potentially during expiration.

    Paradoxical Vocal Cord Motion in Pediatric Patients · 2016 · DOI

  • The literature reviewed demonstrate that very limited data related to the use of NMES on orofacial muscles exist despite the fact that these muscles can be easily accessed by electrical stimulation from the surface.

    A review of electrical stimulation and its effect on lingual, labial and buccal muscle strength · 2014 · DOI

  • There must be at least three hundred scores and anthologies on my teaching bookshelf, representing thousands of individual selections, 80-90% of which are not yet known to me.

    Why I Don't Teach Belting · 2013

  • 14PURPOSE AND METHOD OF SURVEYThere clearly has been no shortage of debate over the use of or by voice teachers; however, there appears to be a lack of data about what techniques are actually being used by contemporary pedagogues.

    The Use of Science and Imagery in the Voice Studio-A Survey of Voice Teachers in the United States and Canada · 2013

  • While consensus exists that a visit to the laryngologist is the first step in determining the source of the problem, there is little consensus as to who should provide the rehabilitation services for voice disorders in singers-the speech-language pathologist, the singing teacher, or perhaps both-and no consensus on the role each discipline plays in the rehabilitative process.

    The Speech Pathologist, the Singing Teacher, and the Singing Voice Specialist: Where's the Line? · 2010

  • The extent to which this factor influences changes in speech production remains to be determined. Although no studies were found which in- vestigated changes in mean sentence rate as a function of age, the results of the present inves- tigation demonstrated that with inter-sentence pause time eliminated, rate of oral reading and impromptu speaking still showed a decrease as a function of age.

    Acoustic Aspects of the Aging Voice · 1972 · DOI

  • 200) that female voice change is &dquo; independent of the first menstruation &dquo;’ and encourage further study of the relationship between menarche and female voice change.

    Fundamental Frequency Characteristics of Adolescent Females · 1970 · DOI

  • this from the Superintendent of Public Instruction, the Pennsylvania speech consultants are more than ready to work to ensure a first-rate education in speech for every school child in the State.

    Pennsylvania's speech consultant system · 1968 · DOI

  • The study was conducted in a single specialized clinic and teachers; therefore, the findings may not be generalizable to the overall teacher population in Georgia.

    Clinical and Voice-Related Characteristics of Teachers Presenting with Voice Disorders in Georgia · 2026 · DOI

  • , persistent post-COVID vocal effects in the recovered group) not explored in depth here.

    Voice-Based COVID-19 Detection: A Physiologically-Grounded Biomarker Approach and the Limits of Transferring the Widmark Alpha Constant - An Analysis of the Coswara-Data Respiratory Sound Corpus (IISc Bangalore) · 2026 · DOI

  • However, it remains unclear how abduction and adduction of the vocal folds influence BI.

    Vocal Fold Opening Position Impacts Bowing Measures in Age‐Related Vocal Atrophy · 2026 · DOI

  • BackgroundCoarse particulate matter (PM10) deposits at the vocal fold (VF) mucosa, yet upper airway responses remain poorly characterized.

    A Human Vocal Fold Organ-On-Chip for Studying Platform-Dependent Mucosal Responses to Particulate Matter · 2026 · DOI

  • This is attributed to significant variability in speech outcomes, small sample sizes, limited comparison groups, diverse participant diagnoses, and inconsistent methodologies and treatment protocols, yielding mixed results.

    Effectiveness of Orofacial Myofunctional Therapy for Speech Sound Disorders in Children: A Systematic Review · 2025 · DOI

  • Future research should examine how these acoustic markers influence audience perception in live settings and consider factors such as accents and actor training in emotive vocal performance.

    The Acoustic Profiles of Emotion: Analyzing the Spoken Voice in Theater Performance · 2025 · DOI

Most-cited papers in Voice and Speech Disorders

Most recent work

Find a gap in your own Voice and Speech Disorders sub-topic

This page shows what the Voice and Speech Disorders literature already flags as unresolved. To narrow it to your specific question, run the guided finder — it searches the gap library on demand and checks candidates against 250M+ OpenAlex works.

Open the Research Gap Finder →

Related topics in Medicine

Substance Abuse Treatment and Outcomes
989 open questions
Artificial Intelligence in Healthcare and Education
607 open questions
Attention Deficit Hyperactivity Disorder
448 open questions
Physical Activity and Health
436 open questions
Smoking Behavior and Cessation
402 open questions
Innovations in Medical Education
364 open questions
Dementia and Cognitive Impairment Research
363 open questions
HIV/AIDS Research and Interventions
342 open questions
67 open questions have been extracted from the limitations and future-work passages of 1,454 Voice and Speech Disorders papers in our library. Each one below links back to the study that raised it, so you can read the original claim in context.

Tools for your next paper

Gaps & Literature SearchFind open questions in any field — 120,000+ open gaps mined from our own library.Pre-CheckIs your paper ready? A Tier 1–5 acceptance probability in seconds.Journal FinderA ranked shortlist of target journals from a 17,500-venue index.Duplicate Publication CheckerCheck prior-publication & salami-slicing risk across 8 sources.Citation GeneratorFreeA DOI or title → APA, MLA, Vancouver, Chicago, BibTeX, RIS. No signup.Graphical Abstract MakerFreeTurn your findings into a colorblind-safe graphical abstract.

Compare the category — Honest roundups of the AI research tools, ours listed alongside the alternatives.

Command palette

Jump anywhere, run any action.