Harmonic Frontier Audio - Vowel Morphing and Formant Shifts (Preview Pack v0.9)

Harmonic Frontier Audio – Vowel Morphing and Formant Shifts (Preview, v0.9) A high-fidelity human vocal dataset designed for AI training, speech research, and expressive voice modeling. Vowel Morphing and Formant Shifts (Preview), created by Harmonic Frontier Audio, provides a compact reference set demonstrating the quality, formatting, and metadata conventions used in the Harmonic Frontier Audio Human Vocality Primitives series. 🔎 Summary This dataset provides high-quality, rights-cleared recordings of continuous vowel morphing and controlled formant shifts — sustained voiced gestures in which vowel identity changes gradually through tongue and lip adjustment while the underlying pitch center remains stable. The recordings emphasize: continuous transitions between contrasting vowel configurations controlled formant movement without pitch glides gradual tongue- and lip-driven resonance changes low- and mid-register vowel behavior stable vowel anchors for comparison These characteristics make the dataset valuable for AI speech modeling, phonetics research, voice synthesis, formant and resonance modeling, and human-aligned vocal control systems. Developed by Harmonic Frontier Audio, this preview follows The Proteus Standard™ for dataset provenance, transparency, and ethical AI use.Learn more about the Proteus Standard → https://harmonicfrontieraudio.com/proteus-standard Full dataset details and licensing information are available at:https://harmonicfrontieraudio.com/datasets/vowel-morphing-formant-shifts If you find this dataset useful, please consider giving it a 🤍 on Hugging Face to help others discover it. 🔊 About Vowel Morphing and Formant Shifts Vowel morphing is the continuous transition from one vowel configuration to another while maintaining a stable pitch center. The perceived vowel change is produced through gradual adjustments of the tongue, lips, and vocal tract shape rather than through melodic pitch movement.Formant shifts are the corresponding changes in vocal tract resonance that move the spectral energy patterns associated with vowel identity. The recording design includes transitions such as ah → eh, eh → ee, ah → oh, oh → oo, and ah → ee, captured in both low and mid register zones, along with stable ah, eh, ee, oh, and oo vowel anchors for comparison. These phenomena are foundational to: vowel and formant-aware speech synthesis continuous resonance and timbre control phonetic and articulatory modeling controllable vowel interpolation in generative voice systems modeling relationships between stable pitch and changing vocal tract configuration This dataset presents a neutral, non-linguistic, non-performative representation of vowel morphing and formant movement.It is not designed to encode semantic speech content, but rather to isolate acoustic primitives underlying continuous vowel transitions and controlled resonance shifts. 📂 Contents Audio Files (.wav) Recorded at 96 kHz / 24-bit WAV format Exported as mono Fade-ins and fade-outs of 3–5 ms applied for consistency No compression, normalization, or creative processing applied High-pass filtered at ~40 Hz to remove subsonic rumble This preview includes 3 representative audio files, selected to demonstrate: continuous vowel transitions with a stable pitch center controlled formant movement driven by tongue and lip adjustment contrasting resonance configurations across vowel states Metadata (.csv) Includes structured fields for: file name sound source type airflow type phonation type gesture and articulation descriptors microphone and recording chain sample rate, bit depth, and dataset version Metadata follows the Harmonic Frontier Audio – Foundations schema. 🎤 Recording Notes Recorded in a treated studio environment using a single-mic setup: Microphone: Rode NT1-A condenser microphone Recording chain: Rode NT1-A → Zoom F8n Pro Captured at 96 kHz / 32-bit float, rendered as 96 kHz / 24-bit mono WAV for release. Performer positioned approximately 3.5 inches from the microphone, with the microphone approximately 10–15 degrees off-axis. Vowel morphs were recorded at approximately 7–9 seconds, with stable vowel anchors approximately 6–8 seconds. Stable pitch centers and natural resonance movement were preserved to retain the acoustic behavior of continuous formant shifts. 🌈 Spectrogram Preview Below is a spectrogram illustrating continuous movement in formant energy, shifting resonance bands, and stable harmonic pitch structure characteristic of controlled vowel morphing: ⚡ Usage This preview pack is designed for: Evaluation of Harmonic Frontier Audio dataset quality and structure Testing AI and DSP systems that model vowel identity, formant movement, and continuous resonance transitions Research in phonetics, speech synthesis, articulatory modeling, and formant-aware voice systems Creative sound design involving controlled vowel interpolation and shifting vocal resonance 👉 Note: This is not a full dataset.The complete Vowel Morphing and Formant Shifts dataset includes a substantially larger set of continuous vowel transitions and stable vowel anchors across low and mid registers and is available for licensing. 💡 Full Dataset Availability This is a preview pack of the Vowel Morphing and Formant Shifts Dataset.The complete dataset is available for commercial licensing. For licensing inquiries:📩 [e-mail] 📥 How to Use This Dataset in Python You can load the Parquet-converted version of this dataset directly with the datasets library: from datasets import load_dataset dataset = load_dataset( "Harmonic-Frontier-Audio/Vowel_Morphing_and_Formant_Shifts_Preview", split="train" ) print(dataset) ⚙️ Note: Parquet conversion and load_dataset() support will be available within 2–3 days of publication. 🔗 Explore More from Harmonic Frontier Audio Human Vocality Primitives Series (Previews) Celtic Constellation Series (Previews) Extended Vocal Techniques Spectrum (Previews) Novelty Gems Cabinet (Previews) (All datasets follow The Proteus Standard™ for ethical dataset provenance and licensing.) 📜 License Released under CC BY-NC 4.0. Free for non-commercial use, testing, and research Commercial licensing available via Harmonic Frontier Audio A formal rights declaration is included in this dataset bundle 📧 Contact Harmonic Frontier Audio📩 [e-mail]🌐 https://harmonicfrontieraudio.com/ 🗒️ Release Notes Version 0.9 (March 2026) – Initial Preview Pack release for Vowel Morphing and Formant Shifts.See CHANGELOG.md for detailed version history. Citation If you use this dataset in your research, please cite: Pullen, B. (2026). Vowel Morphing and Formant Shifts Dataset (Preview) [Data set]. Harmonic Frontier Audio. Zenodo. https://doi.org/10.5281/zenodo.21960038 ORCID: https://orcid.org/0009-0003-4527-0178 BibTeX @dataset{pullen_2026_vowelmorphingandformantshifts_preview, author = {Blake Pullen}, title = {Vowel Morphing and Formant Shifts Dataset (Preview)}, year = {2026}, publisher = {Harmonic Frontier Audio}, version = {0.9}, doi = {10.5281/zenodo.21960038}, url = {https://doi.org/10.5281/zenodo.21960038} }