Extended Vocal Techniques Spectrum (Music)
Structured resonances, controlled transitions, glissandi, and dynamic variations for expressive vocal synthesis.
Structured at the articulation level using documented production workflows and secured under the Proteus Standard™.
Overtone singing is a vocal technique in which a performer sustains a single fundamental pitch while selectively amplifying upper harmonics through precise shaping of the vocal tract. Rather than producing multiple pitches mechanically, the technique exploits the natural harmonic structure of the human voice, allowing individual overtones to emerge as distinct perceptual elements above the fundamental tone.
Acoustically, overtone singing provides a rare and highly controlled window into vocal tract resonance behavior, spectral shaping, and harmonic emphasis. Expressivity arises through fine-grained adjustments of tongue position, mouth shape, and breath control rather than changes in pitch or amplitude. These characteristics make overtone singing particularly well suited for articulation-level analysis and modeling, where disentangling source excitation from resonant filtering and gesture-driven spectral movement is essential.
Key technical details for this dataset — including file counts, duration, delivery format, and session context.
Planned technical specifications and recording standards for this dataset.
Total Files:
Total Files (Preview):
10
Total Duration (Hours):
0.1
Sample Rate (Hz):
96000
Bit Depth (Delivery):
24
Dataset Version:
v0.9
Recording Environment:
Treated Studio
Microphone Configuration:
Rode NT1-A positioned 6-8 inches from mouth
Performer:
Blake Pullen
Recording Dates:
Dec. 6th, 2025
Recording Location:
Las Vegas, NV
Produced using standardized capture, editing, and QC protocols with versioned metadata and Proteus-backed provenance.
An overview of what’s included in this dataset — from articulations and performance styles to session context and recording notes.
This preview dataset contains a curated subset of articulation-focused recordings demonstrating overtone singing techniques performed with controlled vocal production.
The material is intended to illustrate the dataset’s structural approach, capture quality, and technique taxonomy, rather than represent the full scope of the final release.
Included recordings focus on stable fundamental tone production, controlled manipulation of vocal tract resonances, and isolated overtone emphasis, captured without musical accompaniment to support expressive audio modeling, evaluation, and analysis workflows.
The full dataset will expand substantially on this foundation, with broader pitch coverage, extended technique variations, and a significantly larger corpus of recorded material exploring the full expressive and acoustic range of overtone singing.
All audio was recorded in a controlled studio environment using standardized capture, editing, and QC protocols consistent across the Harmonic Frontier Audio catalog.
Source material was captured at 32-bit float to preserve dynamic headroom and fine-grained spectral detail during recording and editing.
Final preview files are delivered as 24-bit PCM for consistency and downstream compatibility.
Recordings were performed by a single vocalist to maintain consistency in vocal anatomy, resonance behavior, and articulation technique across all sessions.
Post-processing was limited to trimming, fade handling, and integrity checks. No creative processing, pitch correction, normalization, or spectral enhancement was applied beyond what was necessary for clean delivery.
A structured breakdown of the expressive building blocks in this dataset — including articulations, dynamics, transitions, and any extended techniques captured during recording.
Unlike clip- or phrase-based datasets, this dataset is structured at the articulation and gesture level. This enables interpretable control, expressive variability, and human-aligned modeling, but significantly increases production complexity and significantly limits who can produce such datasets correctly at scale.
This preview includes representative examples of core overtone singing behaviors, captured in isolation to support articulation-aware modeling and spectral analysis.
Articulations include:
Articulations are recorded without linguistic content to preserve clarity and separability of acoustic behavior.
The preview dataset includes limited examples of gesture-level behavior intended to demonstrate the structure of the full dataset rather than exhaustively cover all techniques.
Gesture types include:
More advanced overtone movement patterns, extended dynamic control, and broader spectral exploration will be included in the full dataset release.
A three-layer provenance and integrity framework ensuring verifiable chain-of-custody, tamper-evident delivery, and spectral fingerprinting for enterprise deployment. These layers are versioned and maintained to support long-term auditability, continuity, and enterprise compliance.
All full datasets from HFA include provenance metadata, session identifiers, and spectral integrity markers as part of The Proteus Standard™ for compliant enterprise deployment.
Captured with expert musicians and vocalists across global traditions — ensuring each dataset carries authentic nuance, human expression, and rights-managed provenance.
Blake Pullen is a multi-disciplinary vocalist, musician, and recording engineer with formal training in vocal performance and extensive experience in controlled vocal production techniques.
His approach to overtone singing in the context of Harmonic Frontier Audio emphasizes repeatability, acoustic clarity, and isolation of core vocal behaviors rather than stylistic or performative expression. This perspective supports dataset creation optimized for machine learning applications, where consistent articulation, controlled resonance, and interpretable acoustic structure are critical.
As the founder of Harmonic Frontier Audio, he performs and records the initial vocal datasets to establish a consistent technical and methodological foundation for the catalog, ensuring that capture standards, technique taxonomy, and provenance protocols are applied rigorously from the outset.
A three-part listening benchmark: a mixed musical demo built from this dataset, the raw source clip, and an AI model’s attempt to reproduce the same prompt.
A musical demonstration created by replacing a state-of-the-art AI-generated lead instrument with original source recordings from this dataset, then arranged and mastered to preserve musical context. This approach allows direct comparison between current-generation model output and real, rights-cleared acoustic source material.
Directly from the dataset: an isolated, unprocessed example of the source recording.
An unmodified output from a current-gen AI model given the same musical prompt. Included to illustrate where today’s systems still differ from real, recorded sources.
An unmodified output from a current-generation AI music model given the same melodic prompt. Because current generative music models do not support overtone-based spectral melody, this example substitutes a conventional high-pitched melodic instrument as a proxy. The result illustrates a structural limitation of today’s systems when attempting to approximate overtone singing techniques.
AI model approximations generated using publicly available state-of-the-art music generation systems.
Harmonic Frontier Audio datasets are licensed directly to research teams, startups, and enterprise partners. Access models and terms vary based on use case, scale, and integration needs.
All datasets are delivered with versioned metadata, documented workflows, and Proteus-backed integrity manifests.
We typically respond to inquiries within 1–2 business days.
This dataset is actively being recorded and prepared. You can request early access, previews, or discuss licensing timelines.
We typically respond within 1–2 business days.