By Ian DeNolfo
Executive Director, The Voice Foundation
Executive Overview
Today, we stand at a definitive inflection point in the interdisciplinary sciences of the human voice. Artificial intelligence (AI) and machine learning (ML) are no longer speculative concepts or distant technologies on the horizon; they are actively and fundamentally reshaping how researchers conduct investigations, how clinicians analyze complex acoustic and physiological data, and how medical professionals care for patients.
For over five decades, The Voice Foundation has served as the global nexus for voice research, education, and clinical practice. As the publisher of the Journal of Voice—the premier peer-reviewed publication dedicated entirely to voice science and medicine—we have watched the field evolve from rudimentary acoustic measurements into a sophisticated, highly quantitative discipline.
What makes the current moment so extraordinary is the velocity of change. Driven by deep neural networks, large language models, and advanced pattern recognition algorithms, AI has transitioned from an experimental curiosity into a foundational pillar of modern otolaryngology and speech-language pathology. An examination of publication data from the Journal of Voice reveals a striking paradigm shift: more than 60 percent of all AI-related papers in the journal’s history have been published in just the last three years.
This article explores the historical foundations of our field, traces the explosive growth of artificial intelligence in voice research, examines breakthrough real-world applications—such as digital biomarkers and clinical chatbots—and outlines the essential ethical framework required to navigate this uncharted territory responsibly.
Detailed Chronology: A Legacy of Innovation Meets Modern Computing
The Roots of Interdisciplinary Voice Care
To understand the profound transformation underway, one must first look back at the origins of modern voice science. In 1969, Dr. Wilbur James Gould founded The Voice Foundation in New York City. At that time, comprehensive, interdisciplinary care for the human voice was virtually nonexistent. Otolaryngologists practiced medicine largely in silos, separated from the speech-language pathologists, vocal pedagogy teachers, and performing artists whose livelihoods depended on vocal health.
Dr. Gould possessed the groundbreaking foresight to bring these diverse groups together. By fostering a collaborative environment, he united medical doctors, scientists, therapists, and performers to share their distinct expertise in the care of the professional voice user.
In 1972, the Foundation hosted its first Annual Symposium—Care of the Professional Voice—which quickly became the premier international gathering for voice professionals. This was followed in 1973 by the inaugural Gala (later named Voices of Summer). For over fifty years, the Foundation has successfully bridged the gap between art and science, and between the clinical laboratory and the theatrical stage.
Since 1989, the organization has been led by Dr. Robert Thayer Sataloff, an internationally renowned otolaryngologist, master clinician, professional singer, and conductor. Dr. Sataloff has authored more than 1,200 publications, including 79 textbooks. Under his visionary leadership, the Foundation relocated its headquarters to Philadelphia and expanded its global footprint, cementing its status as the world’s leading authority on voice science, education, and research. Today, the annual Philadelphia symposium draws hundreds of medical doctors, researchers, academics, and performing artists from every corner of the globe.
Thirty-One Years of AI in Voice Science
While the general public views artificial intelligence as a recent phenomenon sparked by the rollout of consumer-facing generative AI tools, the voice science community has been quietly pioneering computational intelligence for decades.
The Journal of Voice was publishing AI-driven research long before mainstream awareness of machine learning existed. In 1994—thirty-one years ago—the journal published a landmark paper by Rihkanen and colleagues titled "Spectral Pattern Recognition of Improved Voice Quality." Utilizing rudimentary neural networks to analyze acoustic patterns, this research was published the exact same year the World Wide Web was emerging into public consciousness. Voice researchers were deploying AI algorithms before the vast majority of professionals had ever sent an electronic mail message.
However, the trajectory of this research has shifted dramatically in recent years. Historical publication data within the Journal of Voice highlight an exponential curve:
- 1994–2015: 17 papers
- 2016–2019: 27 papers
- 2020–2022: 16 papers
- 2023–2025: 102 papers
In the year 2025 alone, the journal published 51 AI-related papers—surpassing the total number of artificial intelligence articles published during the entire first two decades of our computational journey. This is not mere incremental growth; it represents an exponential transformation of the discipline.
Supporting Context & Metrics: Beyond Citations to Real-World Impact
Academic publishing is frequently judged by citation metrics, but the true measure of scientific literature lies in its practical utility for clinicians, researchers, and educators. Recent usage statistics demonstrate the extraordinary global reach and tangible impact of AI research published in the Journal of Voice.
On average, an AI-focused paper published in the journal is downloaded nearly 1,000 times. However, standout papers have achieved unprecedented distribution. For instance, a seminal study investigating machine learning methodologies for COVID-19 detection via acoustic features has been downloaded over 7,200 times—eleven times the median download rate for articles in its respective issue.
Similarly, our two most-cited papers—a deep learning study by Fang and colleagues (193 citations) and a comprehensive machine learning survey by Hegde and colleagues (147 citations)—have each been accessed nearly 5,000 times. These figures represent active engagement from clinicians, speech-language pathologists, and biomedical engineers seeking practical, scalable tools to enhance patient outcomes.
Landmark Research Reshaping the Field
1. Deep Learning for Voice Pathology Detection
Fang and colleagues’ 2019 study, "Detection of Pathological Voice Using Cepstrum Vectors: A Deep Learning Approach," remains the most-cited AI paper in the journal’s history. This research proved that deep neural networks could identify pathological voice conditions with remarkable precision by evaluating acoustic features completely imperceptible to the human ear.
This foundational work was expanded by Hegde’s survey on automated detection methods, as well as crucial contributions by Al-Nasheri and colleagues in 2017 focusing on Multidimensional Voice Program (MDVP) parameters and correlation functions. More recently, researchers like Chen and Chen (2022) with their work on deep neural networks for voice classification, Fujimura on one-dimensional convolutional neural networks (CNNs), and Cho and Choi on CNN models for laryngoscopic image analysis have continuously pushed the boundaries of diagnostic accuracy.
2. The Voice as a Digital Biomarker
Perhaps the most conceptually transformative advancement in modern medicine is the recognition of the human voice as a digital biomarker—a non-invasive, highly accessible window into systemic neurological, psychological, and respiratory health.
The Journal of Voice has published pioneering studies utilizing automated voice analysis to detect and monitor the progression of Parkinson’s disease. For example, Hemmerling and Wójcik-Pędziwiatr’s 2022 paper on predicting Parkinson’s severity from acoustic voice signals rapidly accumulated 29 citations within three years, paving the way for remote patient monitoring.
Beyond neurology, recent systematic reviews explore voice quality as a digital biomarker for psychiatric conditions such as depression and bipolar disorder. The clinical implications are immense: routine acoustic screening could allow for the early detection of mental health fluctuations, enabling proactive intervention and alleviating the strain on overstretched healthcare systems. Furthermore, machine learning models capable of identifying COVID-19 and other respiratory pathologies from vocal characteristics underscore the voice’s role as a sentinel for general physiological health.
3. AI Chatbots in Clinical Practice
As conversational AI matured, the journal expanded its scope to evaluate large language models (LLMs) in medical decision-making. Dronkers and colleagues’ 2025 paper, "Evaluating the Potential of AI Chatbots in Treatment Decision-making for Acquired Bilateral Vocal Fold Paralysis," garnered 18 citations almost immediately upon release—an exceptional velocity indicating intense scholarly interest.
This work sparked robust academic discourse, including letters to the editor and follow-up investigations into the diagnostic accuracy of models like ChatGPT-4o when evaluating complex laryngeal images. The medical community is actively grappling with the opportunities and hazards of integrating conversational AI into clinical workflows in real time.
Official Statements & Expert Perspectives
To contextualize these technological shifts, we turn to leading voices within our scientific community who view these developments through lenses of computational complexity and institutional ethics.
Dr. Mark Berardi: AI as a Tool for Managing Complexity
Dr. Mark Berardi, whose academic background spans physics and computation, offers a unique perspective on the intersection of AI and voice science. He views machine learning fundamentally as a tool for managing 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 focuses on extracting health information from speech signals to monitor aging and depression. While acquiring voice data has become straightforward, he emphasizes that the true hurdle remains the intrinsic complexity of human communication.
Regarding generative AI, Dr. Berardi maintains a pragmatic view. While large language models may not have entirely rewritten foundational research methodologies overnight, they have eliminated severe operational bottlenecks—particularly in data processing and custom software development. Researchers can now draft bespoke analytical code using natural language prompts, accelerating experimental design.
Intriguingly, Dr. Berardi is also investigating human-AI communication dynamics: how humans alter their speech patterns when conversing with chatbots versus real people, and how "synthetic" communication formats (such as video conferencing) differ from face-to-face dialogue. As linguistic adaptation evolves, the field of voice science may soon need to analyze not just the human voice in isolation, but the human voice in active dialogue with artificial entities.
Dr. Eric Hunter: Embracing Change with Ethical Clarity
Dr. Eric Hunter emphasizes the institutional and systemic changes necessitated by the AI revolution.
"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 points out an inescapable academic reality: large language models and AI-driven platforms are permanently embedded in modern scholarly infrastructure, from word processors to collaborative writing suites. Rather than resisting this technological wave, he issues a clear call to action: the scientific community must establish proactive, transparent guidelines regarding appropriate usage for both authors and peer reviewers.
To maintain academic integrity, Dr. Hunter outlines four foundational pillars for AI integration in research:
- Transparency: Full disclosure of any AI tools utilized in drafting, coding, or data synthesis.
- Accountability: Human authors must retain absolute responsibility for the accuracy and originality of published work.
- Data Security: Strict adherence to patient privacy and institutional review board (IRB) standards when processing vocal biomarkers.
- Editorial Oversight: Continuous adaptation of peer-review policies to evaluate AI-generated content rigorously.
"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 momentum behind AI voice science is sustained by a vast, collaborative international network. Leading contributors to the Journal of Voice represent institutions spanning every populated continent. Prominent researchers driving this movement include Jérôme René Lechien (6 papers), Dimitar Deliyski (5 papers), Stephanie Zacharias (5 papers), Ahmed Yousef (4 papers as first author), Paavo Alku, Leonardo Wanderley Lopes, and Maryam Naghibolhosseini. This decentralized, global commitment ensures that voice science continues to advance through diverse, cross-cultural datasets and rigorous multi-institutional collaboration.
Future Outlook: The Path Forward for Voice Science
As the Journal of Voice looks toward the coming decades, it will remain the premier publishing platform for cutting-edge acoustic research. However, navigating this new era requires deliberate, collective action across three distinct fronts:
- Mindful Engagement: 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.
- Collaborative Ethics: The establishment of ethical guidelines—such as those advocated by Dr. Hunter—cannot be achieved by a single institution. It demands a unified effort from publishers, academic societies, clinicians, and ethicists worldwide.
- Continued Innovation: The 161 AI-focused papers published in our journal represent only the foundation. Every clinician, speech-language pathologist, and engineer possesses unique insights that can enrich our collective understanding of human 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 identity. It carries the nuances of our health, our psychological state, and our innermost selves in ways that no other biological signal can replicate.
Now, for the first time in human history, we possess computational tools sophisticated enough to genuinely decode that complexity—to uncover what the voice reveals about our brains, our bodies, and our overall wellbeing. These technologies promise to extend the reach of expert clinicians, detect subtle pathology before irreversible damage occurs, and democratize access to high-quality voice care across the globe.
We stand at an extraordinary moment in time, and the Journal of Voice is proud to stand at its very center. The next decade promises discoveries we are only beginning to imagine, and we look forward to sharing them with the global scientific community.
About the Author
Ian DeNolfo is Executive Director of The Voice Foundation, which publishes the Journal of Voice. A graduate of The Juilliard School and The Curtis Institute of Music, he formerly performed as a leading tenor at opera houses worldwide before transitioning his career to arts administration and scientific leadership at The Voice Foundation.
