By Ian DeNolfo Executive Director, The Voice Foundation
Executive Overview
Voice science stands at a profound and historic inflection point. Today, the convergence of artificial intelligence (AI), machine learning (ML), and advanced acoustic engineering is fundamentally reshaping how researchers conduct investigations, how clinicians analyze complex data, and how practitioners care for patients. This digital transformation does not represent a sudden disruption; rather, it is the acceleration of a decades-long pursuit to decode the most intricate instrument known to humanity—the human voice.
For over fifty years, The Voice Foundation and its flagship publication, the Journal of Voice, have served as the intellectual epicenter of interdisciplinary voice research. Long before the mainstreaming of neural networks or the emergence of consumer-facing generative AI, our community recognized the profound potential of computational models to unlock hidden dimensions of vocal physiology and pathology.
An analysis of our publication archives reveals an astonishing trajectory. What began as experimental computational linguistics in the mid-1990s has evolved into an exponential surge of cutting-edge research. In the last three years alone, the Journal of Voice has published over 100 AI-centric studies, with 2025 yielding a record 51 papers in a single year. These investigations transcend traditional academic citations, driving thousands of real-world downloads by clinicians, otolaryngologists, speech-language pathologists, and computational scientists across the globe.
As we navigate this new era—where the human voice is increasingly understood as a non-invasive digital biomarker for systemic health—our community must balance rapid technological adoption with rigorous ethical frameworks. This report examines the historical foundations, landmark breakthroughs, expert perspectives, and future horizons defining the intersection of artificial intelligence and voice science.
A Legacy of Innovation: Bridging Art and Science
To understand the modern integration of artificial intelligence in voice science, one must first look back at the visionary roots of The Voice Foundation. In 1969, Dr. Wilbur James Gould founded the organization in New York City during an era when comprehensive, interdisciplinary care for the human voice was virtually non-existent. Dr. Gould possessed the extraordinary foresight to break down traditional academic and clinical silos, bringing together physicians, voice scientists, speech-language pathologists, performing artists, and master teachers to share expertise in the preservation and rehabilitation of the professional voice.
This collaborative ethos materialized into landmark traditions. In 1972, the Foundation hosted its inaugural Annual Symposium—Care of the Professional Voice—which has since grown into the premier international gathering for voice professionals. This was followed in 1973 by the first Foundation Gala (later renamed Voices of Summer). For over five decades, these initiatives have successfully bridged the gap between the art of performance and the rigor of clinical science.
Since 1989, the Foundation has operated under the visionary leadership of Dr. Robert Thayer Sataloff, an internationally renowned otolaryngologist, professional singer, and conductor. Having authored more than 1,200 publications, including 79 textbooks, Dr. Sataloff guided the Foundation’s relocation to Philadelphia, where it continues to expand its global footprint. Today, our annual Philadelphia symposium draws hundreds of medical, scientific, and academic specialists from every continent, while the Journal of Voice remains the undisputed gold standard for peer-reviewed research in voice science and medicine.
Chronology of Computation: 30 Years of AI in the Journal of Voice
While contemporary media often frames artificial intelligence as a recent phenomenon born out of the 2020s, the historical record tells a radically different story. The Journal of Voice has been publishing peer-reviewed research on artificial intelligence and neural networks for over three decades—longer than most people realize.
In 1994—thirty-one years ago, concurrent with the public emergence of the World Wide Web—the journal published a pioneering paper by Rihkanen and colleagues titled "Spectral Pattern Recognition of Improved Voice Quality." This study utilized nascent neural network architecture to analyze human voice parameters. In essence, the Journal of Voice was publishing machine learning research before the vast majority of professionals had ever sent an electronic mail message.
The Exponential Publication Timeline
For the first two decades following that initial publication, AI research within voice science progressed steadily but incrementally. However, the timeline over the past decade reveals a dramatic, exponential acceleration:
1994–2015 (The Foundation Era): 17 papers exploring early neural networks and acoustic pattern recognition.
2016–2019 (The Machine Learning Expansion): 27 papers leveraging advanced vector analysis and early machine learning algorithms.
2020–2022 (The Deep Learning Transition): 16 papers establishing deep neural networks as viable clinical tools.
2023–2025 (The Exponential Boom): 102 papers published in just three years, completely transforming the literature base.
In the single year of 2025, the Journal of Voice published 51 AI-related papers—surpassing the total output of the journal’s first twenty years combined. This dramatic leap represents a fundamental paradigm shift from theoretical exploration to active, real-world clinical integration.
Supporting Context & Real-World Impact
Academic metrics are frequently confined to citation counts, but the true measure of scientific research lies in its active application by frontline practitioners. Usage statistics for AI-related articles in the Journal of Voice demonstrate extraordinary global engagement.
The average AI-focused paper published in our journal is downloaded nearly 1,000 times—a testament to the high demand for computational insights among clinicians. Furthermore, individual landmark studies have achieved unprecedented reach:
COVID-19 Detection via Machine Learning: Our most-accessed AI paper, examining acoustic algorithms for respiratory virus screening, has been downloaded over 7,200 times—eleven times the median download rate for articles within its issue.
Deep Learning for Pathology Detection: Fang and colleagues’ 2019 study on cepstrum vectors has garnered 193 citations and nearly 5,000 downloads.
Comprehensive Surveys: Hegde’s machine learning survey paper has secured 147 citations and a comparable 5,000 downloads, serving as essential foundational reading for incoming researchers.
These figures illustrate that clinicians, speech-language pathologists, and biomedical engineers are actively turning to computational literature to acquire practical, actionable diagnostic tools.
Landmark Research Reshaping the Field
Deep Learning for Voice Pathology Detection
The integration of deep learning into laryngology has unlocked diagnostic capabilities that bypass human perceptual limitations. Fang and colleagues’ milestone 2019 study, "Detection of Pathological Voice Using Cepstrum Vectors: A Deep Learning Approach," proved that deep neural networks could identify subtle vocal pathologies with remarkable precision by analyzing acoustic features imperceptible to the human ear.
Subsequent research has systematically expanded upon these foundations. Hegde’s comprehensive landscape mapping provided a structural roadmap for automated voice disorder detection. In 2017, Al-Nasheri et al. contributed highly influential papers focusing on Multidimensional Voice Program parameters and correlation functions. More recently, investigators like Chen and Chen (deep neural networks for voice classification), Fujimura (one-dimensional convolutional neural networks), and Cho and Choi (comparative CNN models for laryngoscopic image analysis) have continually pushed the boundaries of diagnostic accuracy.
Voice as a Digital Biomarker for Systemic Health
Perhaps the most philosophically and clinically transformative concept emerging from contemporary voice science is the classification of the voice as a digital biomarker—a non-invasive, continuous window into an individual’s systemic and neurological health.
Groundbreaking studies published in our pages have demonstrated the viability of voice analysis in detecting and monitoring neurodegenerative disorders such as Parkinson’s disease. For example, Hemmerling and Wójcik-Pędziwiatr’s 2022 paper on predicting Parkinson’s severity from acoustic signals has rapidly accumulated citations, paving the way for remote patient monitoring.
Beyond neurology, recent systematic reviews have explored voice quality as a digital biomarker for psychiatric conditions, including major depressive disorder and bipolar disorder. The clinical implications are profound: routine acoustic screenings could enable early mental health interventions, alleviating the immense burden currently facing global healthcare systems. Similarly, machine learning models assessing respiratory health via vocal signatures demonstrate how acoustic analytics can serve as an early sentinel for pulmonary disease.
AI Chatbots in Clinical Decision-Making
As conversational artificial intelligence matures, the Journal of Voice has captured the medical community’s immediate engagement with generative models. A prime example is Dronkers and colleagues’ 2025 paper, "Evaluating the Potential of AI Chatbots in Treatment Decision-making for Acquired Bilateral Vocal Fold Paralysis," which rapidly accumulated 18 citations within months of publication—an extraordinary velocity for scholarly impact.
This work catalyzed numerous academic responses, including investigations into ChatGPT-4o’s proficiency in evaluating laryngeal imagery. The field is actively and transparently grappling with both the promises and perils of incorporating conversational AI into sensitive clinical workflows.
Expert Perspectives: Balancing Complexity and Ethics
To contextualize these technological shifts, we turn to leading voices within our scientific community who bridge computational science and clinical practice.
Dr. Mark Berardi: AI as a Tool for Managing Complexity
Dr. Mark Berardi brings a unique analytical lens to voice science, grounded in physics and computation. He views machine learning not as a replacement for human expertise, but as an essential instrument for managing profound biological complexity.
"Machine learning and AI are tools to help with complexity, and communication is incredibly complex in its neurobiological and physiological processes. So I think the application is warranted," Dr. Berardi notes.
His current research investigates voice-based digital biomarkers for aging and depression. While acquiring vocal signals has become frictionless, the true hurdle remains the intrinsic complexity of human communication—an arena where AI excels. Regarding generative AI, Dr. Berardi offers a pragmatic assessment: while it may not have instantly rewritten foundational theories, it has effectively shattered technical bottlenecks in data processing and custom code generation through natural language prompts.
Furthermore, Dr. Berardi is pioneering research into human-AI communication itself. By examining how individuals alter their linguistic patterns when conversing with chatbots versus humans—or how "synthetic" interactions via Zoom differ from face-to-face dialogue—his work suggests that voice science must soon expand to decode human speech in direct conversation with machines.
Dr. Eric Hunter: Embracing Change with Ethical Clarity
Dr. Eric Hunter emphasizes the institutional and workflow implications of artificial intelligence across academia and clinical practice.
"These tools aren’t just novelties," Dr. Hunter observes. "They are rapidly becoming integrated into how we conduct literature reviews, organize data, extract themes from large bodies of text, and even summarize findings."
Dr. Hunter stresses that large language models and AI-driven platforms are permanently embedded into scholarly infrastructure, spanning manuscript preparation, peer review, and collaborative data analysis. Rather than resisting this technological wave, he issues a vital call to action: our community must proactively establish clear, standardized guidelines for appropriate usage.
To ensure academic integrity, Dr. Hunter outlines four essential operational principles for scholars and reviewers:
Transparent Disclosure: Explicitly documenting where and how AI tools were utilized in the research or drafting process.
Human Accountability: Maintaining absolute authorial responsibility for the factual accuracy and intellectual integrity of published work.
Data Privacy Protection: Ensuring that patient data and proprietary vocal samples are never compromised through unsecured third-party AI interfaces.
Editorial Vigilance: Equipping peer reviewers with the tools and standards necessary to evaluate AI-assisted submissions objectively.
“Our field will benefit most,” Dr. Hunter concludes, “if we embrace the productivity these tools offer while also building a shared ethical framework for their responsible use.”
A Global Research Community
The rapid ascent of AI in voice science is propelled by a vast, interconnected global network of laboratories and clinical institutions. The intellectual momentum of the Journal of Voice is sustained by pioneering authors and co-authors spanning multiple continents.
Prominent contributors include Jérôme René Lechien (6 papers), Dimitar Deliyski (5 papers), Stephanie Zacharias (5 papers), and Ahmed Yousef (4 papers as first author), alongside Paavo Alku, Leonardo Wanderley Lopes, and Maryam Naghibolhosseini (4 papers each). These researchers, working alongside dozens of international teams, represent a unified global commitment to decoding the human voice through advanced computational modeling.
The Path Forward: Strategic Imperatives
As the Journal of Voice charts its course into the next decade, we remain steadfast in our mission to publish rigorous, boundary-pushing research while upholding the highest standards of scientific integrity. However, maximizing the potential of artificial intelligence requires decisive, collective action across three core pillars:
Thoughtful Engagement with Complexity: Researchers and clinicians must approach AI tools as amplifiers of human expertise rather than replacements for clinical judgment. Understanding both the immense capabilities and the algorithmic limitations of these models is paramount.
Establishment of Shared Ethical Frameworks: As Dr. Hunter emphasizes, developing comprehensive ethical guidelines is an industry-wide imperative. No single institution can shoulder this responsibility alone; our entire multidisciplinary ecosystem must collaborate to set ethical standards.
Continuous Knowledge Sharing: The 161 AI-focused papers published in our journal represent merely the foundation. Every clinician, speech-language pathologist, and engineer possesses unique practical insights that can advance our collective understanding of vocal health.
An Extraordinary Moment
For hundreds of thousands of years, the human voice has served as our primary instrument of connection, emotional expression, and personal identity. It carries the nuances of our psychological state, the vitality of our physical bodies, and the essence of our humanity in a manner matched by no other physiological signal.
Now, for the first time in human history, we possess technological tools sophisticated enough to genuinely comprehend that complexity—to decode what acoustic signatures reveal about our brains, our bodies, and our overall wellbeing. We have instruments that extend the diagnostic reach of expert clinicians, detect subtle pathology before acute symptoms manifest, and democratize access to high-quality voice care across the globe.
We are living through an extraordinary moment in scientific history, and the Journal of Voice stands proudly at its center. The coming decade promises even greater discoveries, and we look forward to sharing them with the global community as we continue to build bridges between art, science, medicine, and technology.
