Human Vocality Primitives

Whisper & Aspiration

Whisper phonation with varying pressure, turbulence, and vowel shaping.

FULL DATASET

Human Vocality Primitives

This dataset is currently in production. Preview audio and full specifications will be added as they become available.

This is a preview release provided via Hugging Face for evaluation purposes. Initial recording passes are available to assess capture quality, labeling structure, and dataset relevance. The full dataset will be delivered privately with complete Proteus provenance, integrity, and documentation upon licensing.

This dataset is complete and available for licensing. A public preview subset will be released via Hugging Face on a rolling basis.

Whisper and aspiration are airflow-driven vocal behaviors produced without sustained vocal fold vibration, relying instead on controlled breath, glottal configuration, and vocal tract shaping to generate sound. In these techniques, acoustic energy is created primarily through turbulent airflow rather than harmonic excitation, resulting in noise-shaped vocal output with no stable fundamental pitch. Expressive control emerges through subtle modulation of airflow intensity, mouth shape, articulatory configuration, and transitions into and out of silence rather than changes in loudness or pitch.

Acoustically, whisper phonation and aspiration occupy a broadband, noise-dominant timbral space characterized by diffuse spectral energy, formant-shaped filtering, and fine-grained temporal variation. Expressivity is conveyed through airflow texture, articulatory gesture timing, and the interaction between breath noise and the resonant properties of the vocal tract. These characteristics make whisper and aspiration particularly well suited for modeling unvoiced vocal behavior, breath-aware speech systems, and airflow-centric sound analysis, where precise control of onset behavior, noise structure, and repeatable articulatory gestures is essential.

Audio Demonstrations

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.

PRODUCED REFERENCE

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.

RAW DATASET CLIP

Directly from the dataset: an isolated, unprocessed example of the source recording.

AI MODEL BENCHMARK

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.

AI model approximations generated using publicly available state-of-the-art music generation systems.