ARTI-6: Towards Six-dimensional Articulatory Speech Encoding

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lee, Jihwan, Foley, Sean, Lertpetchpun, Thanathai, Huang, Kevin, Lee, Yoonjeong, Feng, Tiantian, Goldstein, Louis, Byrd, Dani, Narayanan, Shrikanth
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914279278510080
author Lee, Jihwan
Foley, Sean
Lertpetchpun, Thanathai
Huang, Kevin
Lee, Yoonjeong
Feng, Tiantian
Goldstein, Louis
Byrd, Dani
Narayanan, Shrikanth
author_facet Lee, Jihwan
Foley, Sean
Lertpetchpun, Thanathai
Huang, Kevin
Lee, Yoonjeong
Feng, Tiantian
Goldstein, Louis
Byrd, Dani
Narayanan, Shrikanth
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21447
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARTI-6: Towards Six-dimensional Articulatory Speech Encoding
Lee, Jihwan
Foley, Sean
Lertpetchpun, Thanathai
Huang, Kevin
Lee, Yoonjeong
Feng, Tiantian
Goldstein, Louis
Byrd, Dani
Narayanan, Shrikanth
Audio and Speech Processing
Artificial Intelligence
Computation and Language
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.
title ARTI-6: Towards Six-dimensional Articulatory Speech Encoding
topic Audio and Speech Processing
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2509.21447