top of page
Hero image for “The Embodiment Gap” by Joseph Stanek featuring a split portrait of a human singer and AI-generated synthetic face divided by glowing blue light, symbolizing the divide between embodied human vocal production and artificial intelligence in singing voice pedagogy.

THE EMBODIMENT GAP

Conceptual Foundations for
Singing Voice Pedagogy in the Age of AI

Accepted for publication • Forthcoming in the Journal of Singing
 

Anticipated Publication:  2027

The Embodiment Gap is a proposed theoretical construct describing the increasing inability to treat audible vocal output as reliable evidence of verifiable embodied human vocal production, as AI-generated singing becomes acoustically indistinguishable from human performance.

Developed by Joseph Stanek and forthcoming in the Journal of Singing (National Association of Teachers of Singing), the article examines how advances in artificial vocal synthesis challenge long-standing assumptions about authenticity, physiology, and evidentiary listening in singing voice pedagogy.

embodiment gap noun.

a proposed theoretical construct describing the increasing inability to treat audible vocal  output alone as reliable evidence of embodied human vocal production due to advances in AI-generated singing and synthetic voice technologies.*†

*Proposed by Joseph Stanek in forthcoming Journal of Singing research on synthetic (AI-generated) voice.

†Clarification

In this framework, the embodiment gap refers specifically to the evidentiary relationship between audible vocal output and verifiable embodied human vocal production — not to emotional disengagement, somatic practice, or performance aesthetics.

FORTHCOMING IN THE JOURNAL OF SINGING

The Embodiment Gap: Conceptual Foundations for Singing Voice Pedagogy in the Age of AI

Author: Joseph Stanek

Institution: Tour de Fierce Research, New York, NY

ORCID: 0009-0003-9390-4809

Status: Accepted for publication | Journal of Singing (National Association of Teachers of Singing)

Acceptance Date: April 29, 2026

About This Article

This forthcoming article introduces the embodiment gap as a framework for understanding how artificial intelligence is reshaping assumptions about the singing voice.

 

The publication proposes terminology and conceptual tools intended to support future discussion within singing voice pedagogy, voice authenticity research, and synthetic voice evaluation.

 

Rather than focusing on whether AI-generated singing can sound convincing, the framework examines the growing challenge of determining what audible vocal sound can reliably communicate about embodied human vocal production.

 

Additional details remain under publication embargo pending release in the Journal of Singing.

Keywords

voice pedagogy · artificial intelligence · embodiment gap · synthetic singing · AI-generated singing · human voice · singing voice · voice training · forensic listening · synthetic voices

Key Topics

  • AI-generated singing

  • Synthetic voices

  • Singing voice pedagogy

  • Vocal authenticity

  • Voice cloning

  • Embodied voice production

  • Forensic listening

  • Artificial voice synthesis

  • Human voice identity

  • Physiological plausibility

  • Vocal provenance

  • Diagnostic listening

  • Ethics of synthetic performance

Publication Status

  • Accepted for publication in the Journal of Singing (National Association of Teachers of Singing)

  • Acceptance Date: April 29, 2026

  • Author: Joseph Stanek
    Institution: Tour de Fierce Research, New York, NY
    ORCID: 0009-0003-9390-4809

About the Journal of Singing

The Journal of Singing is the official peer-reviewed journal of the National Association of Teachers of Singing (NATS) — the largest professional association of teachers of singing in the world, with members across more than 30 countries. It is the flagship scholarly publication of the field of singing voice pedagogy.

About the Author

Joseph Stanek is the founder and lead researcher of Tour de Fierce Research, an independent interdisciplinary research initiative based in New York, NY, examining the human voice as a site of embodied cognition, emotional regulation, and meaning-making at the intersection of professional vocal practice, neuroaesthetics, and emerging technologies. His research interests include performance anxiety and autonomic regulation, voice identity and perception, psychoacoustics, and the relationship between artists and algorithmic AI systems. His research profile is featured by the Renée Fleming NeuroArts Resource Center, connecting scientists, artists, and institutions advancing the NeuroArts field globally.


Stanek is the author of the NeuroArts Expansion Series, a trailblazing monograph sequence deposited on Zenodo under open-access license, advancing named theoretical constructs including Artist-Led Origination, Applied Aesthetic Contexts, Diachronic Aesthetic Knowledge, Reciprocal Embodied Literacy, and the ETUDE framework. His forensic audit of the 2024 International Songwriting Competition, documenting AI-generated entries receiving awards in violation of competition policy, is indexed across major research platforms.


As a performer and producer, Stanek has appeared on Broadway, at Carnegie Hall, and at the Metropolitan Opera, and has produced nationally broadcast television specials for NBC, ABC, and PBS. His work in music education was celebrated at the 2019 GRAMMY on the Hill Awards for Philanthropy.

FAQ

What is the embodiment gap?

The embodiment gap is a proposed theoretical framework describing the increasing inability to treat audible vocal output alone as reliable evidence of verifiable embodied human voice production, due to advances in AI-generated singing and synthetic voice technologies.

Who developed the embodiment gap framework?

The embodiment gap framework was developed by Joseph Stanek as part of ongoing research into artificial intelligence, synthetic singing, and singing voice pedagogy.

Is the embodiment gap about emotional singing or somatic voice work?

No. The embodiment gap refers specifically to the evidentiary relationship between audible vocal output and verifiable embodied human vocal production — not to emotional expression, somatic practice, or performance aesthetics.

Where will the embodiment gap framework be published?

The framework is forthcoming in the Journal of Singing, the scholarly journal of the National Association of Teachers of Singing (NATS).

Contact

For speaking engagements, research collaboration, press, or general inquiries — get in touch.

Return to the Tour de Fierce Research Main Page >

bottom of page