By Ian DeNolfo Executive Director, The Voice Foundation
Executive Overview
Today, we stand at a definitive inflection point in voice science—a historic juncture where artificial intelligence (AI) and machine learning (ML) are fundamentally reshaping how researchers conduct scientific studies, analyze complex acoustic data, and deliver precision care to patients. For centuries, the human voice has served as our primary vehicle for connection, emotional expression, and identity, conveying physiological and psychological states in ways no other biological signal can match. Yet, the sheer neurobiological and physiological complexity of vocal production has long challenged clinicians and researchers alike.
Now, for the first time in medical and scientific history, we possess computational tools sophisticated enough to untangle this complexity. From automated pathology detection to the conceptualization of the human voice as a non-invasive digital biomarker for systemic health, AI is accelerating the pace of discovery. At the epicenter of this transformation is The Journal of Voice and its parent organization, The Voice Foundation. Far from being a recent bandwagon, our community has pioneered the intersection of AI and voice science for over three decades. As publication rates soar exponentially—with more than 60% of all AI-related papers in our journal’s history published in just the last three years—we are witnessing a paradigm shift that promises to redefine the boundaries of medicine, technology, and art.
A Legacy of Innovation: Bridging Art and Science
To understand the magnitude of today’s technological leap, one must look back at the visionary roots of The Voice Foundation. Founded in New York City in 1969 by Dr. Wilbur James Gould, the Foundation emerged during an era when interdisciplinary care for the human voice was virtually nonexistent. Dr. Gould possessed the remarkable foresight to bring together a diverse coalition of physicians, vocal scientists, speech-language pathologists, performing artists, and singing teachers. This collaborative ecosystem was designed to pool cross-disciplinary expertise specifically focused on the care of the professional voice user.
In 1972, the Foundation hosted its inaugural Annual Symposium: Care of the Professional Voice, quickly followed by its first Gala (later christened Voices of Summer) in 1973. For more than five decades, these platforms have successfully bridged the historical divide between art and science, connecting the clinical examining room with the theatrical stage.
Since 1989, the Foundation has operated under the visionary leadership of Dr. Robert Thayer Sataloff, an internationally renowned otolaryngologist who is also a professional singer and conductor. Dr. Sataloff has authored more than 1,200 publications, including 79 textbooks. Under his stewardship, the Foundation relocated its headquarters to Philadelphia and dramatically expanded its global influence through rigorous scientific research and educational outreach. Today, the annual Philadelphia Symposium draws hundreds of medical, scientific, academic, and artistic professionals from across the globe, while our flagship publication, the Journal of Voice, remains the premier peer-reviewed journal dedicated exclusively to voice science and medicine.
Detailed Chronology: Thirty Years of AI Research in Voice Science
A common misconception in the contemporary tech landscape is that artificial intelligence in medicine is a phenomenon born of the 2020s. In reality, the Journal of Voice has been publishing pioneering AI and machine learning research for over three decades—longer than the public consciousness has even been aware of the World Wide Web.
The Genesis: 1994
The historical journey of AI within our pages began in 1994, thirty-one years ago, with a landmark paper authored by Rihkanen and colleagues titled "Spectral Pattern Recognition of Improved Voice Quality." Utilizing rudimentary neural networks to analyze acoustic signals, this study proved that artificial intelligence could parse subtle voice characteristics. To put this into perspective, this research was published the exact same year the World Wide Web was commercializing, and before most academics had ever sent a professional email.
The Slow Burn and Exponential Rise
For the next two decades, AI research in voice science grew steadily, albeit incrementally, as computing power and algorithmic models matured:
1994–2015: 17 papers published.
2016–2019: 27 papers published.
2020–2022: 16 papers published.
2023–2025: 102 papers published.
The publication timeline tells a dramatic story of sudden, exponential acceleration. In the year 2025 alone, the Journal of Voice published 51 AI-related papers—surpassing the total output of the journal’s entire first twenty years combined. This is not gradual evolutionary growth; it is an exponential transformation that is actively rewriting the rules of clinical diagnostics and academic inquiry.
Supporting Context and Real-World Impact
Metrics tell only part of the story, but in the case of AI research within the Journal of Voice, the numbers highlight an insatiable global appetite for computational voice tools. These publications are not merely accumulating academic citations; they are being actively downloaded, read, and implemented by clinicians and researchers worldwide.
The average AI-focused paper published in our journal is downloaded nearly 1,000 times—a testament to its broad practical utility. Furthermore, individual milestones are staggering:
COVID-19 Detection Study: Our most-accessed AI paper—a machine learning investigation into acoustic COVID-19 detection—has amassed over 7,200 downloads, representing eleven times the median viewership for articles within its issue.
Fang et al. (Deep Learning): The most-cited paper in our journal’s AI history, focusing on deep neural networks for voice pathology detection, has accumulated 193 citations and nearly 5,000 downloads.
Hegde et al. (Machine Learning Survey): Serving as an indispensable roadmap for newcomers to the field, this comprehensive survey has garnered 147 citations and close to 5,000 downloads.
These high engagement metrics confirm that clinicians, otolaryngologists, and speech-language pathologists are actively seeking practical, technology-driven tools to enhance patient outcomes.
Landmark Research Reshaping the Field
Deep Learning for Voice Pathology Detection
The foundational work of Fang and colleagues in 2019 ("Detection of Pathological Voice Using Cepstrum Vectors: A Deep Learning Approach") shattered previous diagnostic boundaries by proving that deep neural networks could detect pathological alterations in the voice using acoustic features entirely imperceptible to the human ear.
This work paved the way for subsequent technical milestones, including Hegde’s expansive machine learning surveys, Al-Nasheri’s 2017 multidimensional parameter analyses, Chen and Chen’s deep neural network classifications, Fujimura’s work with one-dimensional convolutional neural networks (CNNs), and Cho and Choi’s comparative analyses of CNN models applied to laryngoscopic imaging. Each successive study builds on its predecessor, continually expanding the limits of diagnostic precision.
The Voice as a Digital Biomarker
Perhaps the most paradigm-shifting concept to emerge from recent literature is the classification of the human voice as a digital biomarker—a non-invasive, continuous window into systemic health.
Groundbreaking research published in our pages has demonstrated the efficacy of voice analysis in detecting and monitoring neurodegenerative disorders such as Parkinson’s disease. Notably, Hemmerling and Wójcik-Pędziwiatr’s 2022 paper on predicting Parkinson’s severity via voice signals has garnered 29 citations in just three years, accelerating the shift toward clinical translation.
Beyond neurology, systematic reviews exploring voice quality as a digital biomarker for clinical depression and bipolar disorder offer profound possibilities. The prospect of tracking mental health fluctuations through routine vocal telemetry could dramatically reduce the burden on overstretched healthcare systems and enable proactive, early-stage psychiatric interventions. Similarly, machine learning evaluations of respiratory health during the global pandemic underscored how vocal signatures can serve as early sentinels for systemic illness.
AI Chatbots in Clinical Decision-Making
As conversational AI matured, the Journal of Voice began exploring its integration into direct medical workflows. A prime example is Dronkers and colleagues’ 2025 study, "Evaluating the Potential of AI Chatbots in Treatment Decision-making for Acquired Bilateral Vocal Fold Paralysis," which rapidly accumulated 18 citations within its first year of publication. This paper sparked robust academic dialogue, including subsequent letters to the editor and investigative responses analyzing the diagnostic accuracy of models like ChatGPT-4o in interpreting complex laryngeal images. The medical community is actively and transparently wrestling with the profound responsibilities of conversational AI at the bedside.
Official Statements and Expert Perspectives
To successfully navigate this technological wave, the voice science community relies on the insights of multidisciplinary leaders who understand both the promise and the pitfalls of computational integration.
Dr. Mark Berardi: AI as a Tool for Complexity
Dr. Mark Berardi brings a unique, dual perspective rooted in physics and computation. He views artificial intelligence primarily as an indispensable instrument for managing overwhelming systemic 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’s current research focuses on extracting health insights from vocal biomarkers related to aging and depression. While acquiring voice signals is technologically straightforward today, he notes that decoding the underlying neurobiological communication system remains the true hurdle—a challenge tailor-made for machine learning.
Addressing generative AI, Dr. Berardi offers a pragmatic appraisal:
"It can address some of the bottlenecks we have in research—particularly in coding and data processing. I can now quickly create bespoke code and edit it with natural language prompts."
Furthermore, Dr. Berardi is spearheading research into human-AI communication itself, analyzing how humans alter their linguistic and phonetic patterns when interacting with synthetic entities versus real people. As digital communication mediums like Zoom and conversational chatbots dominate modern life, voice science must expand to understand human vocal behavior in conversation with machines.
Dr. Eric Hunter: Embracing Change with Ethical Clarity
Dr. Eric Hunter emphasizes that institutional adaptation is no longer optional. The integration of AI into academic and clinical frameworks is an undeniable reality:
"These tools aren’t just novelties. They are rapidly becoming integrated into how we conduct literature reviews, organize data, extract themes from large bodies of text, and even summarize findings."
From natural language tools like NotebookLM and Claude to embedded assistants within standard office suites, AI is permanently altering scholarly infrastructure. However, Dr. Hunter issues a vital call to action for the academic community: rather than resisting the tide, researchers must establish proactive, transparent guidelines regarding appropriate usage.
Dr. Hunter outlines four foundational pillars for ethical AI integration in academic publishing:
Absolute Transparency: Clear disclosure of where and how AI tools were utilized in manuscript preparation and data analysis.
Human Accountability: Maintaining strict human oversight; authors remain entirely responsible for the factual accuracy and integrity of their work.
Data Privacy and Security: Ensuring patient-derived voice data is protected against unauthorized training ingestion or privacy breaches.
Equitable Access: Ensuring that computational tools do not create insurmountable economic barriers for researchers in developing nations.
"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 evolution of AI-driven voice science is not the product of isolated laboratories working in silos; it is driven by a vibrant, interconnected global community.
Key contributors shaping the pages of the Journal of Voice span continents and disciplines. Prolific authors such as 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 (4 papers each) represent just a fraction of the international network of pioneers applying machine learning to vocal pathology. United by a shared commitment to empirical rigor, this global collective is defining the future of otolaryngology, speech pathology, and acoustic engineering.
Future Outlook and the Path Forward
As the Journal of Voice looks toward the horizon, our editorial mission remains steadfast: to publish uncompromising, high-integrity research that expands scientific boundaries while maintaining rigorous peer-review standards. However, our community must collectively confront three imperative challenges moving forward:
Thoughtful Engagement: We must learn the true capabilities and limitations of AI tools, utilizing them to amplify human expertise rather than abdicate clinical and scientific judgment.
Collaborative Ethics: Dr. Hunter’s vision for a unified ethical framework requires a concerted, global effort across institutions, governing bodies, and publishing houses.
Continuous Discovery: The 161 AI-focused papers published to date represent merely the foundation. Every clinician, educator, and laboratory scientist holds unique insights capable of advancing our collective understanding.
The human voice has carried our emotions, our health, and our identity for millennia. Today, for the first time in history, we possess computational instruments powerful enough to truly decode its hidden complexities. By bridging our rich historical legacy with the boundless potential of artificial intelligence, The Voice Foundation and the Journal of Voice remain firmly at the center of a medical revolution. The next decade promises even more profound discoveries—and we look forward to sharing them with the world.
