Year: 2025
Type: preprint
Abstract: We propose ARTI-6, a compact six-dimensional articulatory speech encoding framework derived from real-time MRI data that captures crucial vocal tract regions including the velum, tongue root, and larynx. ARTI-6 consists of three components: (1) a six-dimensional articulatory feature set representing key regions of the vocal tract; (2) an articulatory inversion model, which predicts articulatory features from speech acoustics leveraging speech foundation models, achieving a prediction correlation of 0.87; and (3) an articulatory synthesis model, which reconstructs intelligible speech directly from articulatory features, showing that even a low-dimensional representation can generate natural-sounding speech. Together, ARTI-6 provides an interpretable, computationally efficient, and physiologically grounded framework for advancing articulatory inversion, synthesis, and broader speech technology applications. The source code and speech samples are publicly available.
Source: arXiv (Cornell University)
Authors: Lee, Jihwan, Foley, Sean, Lertpetchpun, Thanathai, Huang, Kevin, Lee, Yoonjeong, Feng, Tiantian, Goldstein, Louis, Byrd, Dani, Narayanan, Shrikanth
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7083844396
Cites:
Cited by:
Related to: