Acoustic-to-Articulatory Inversion of Clean Speech Using an MRI-Trained Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Azzouz, Sofiane, Vuissoz, Pierre-André, Laprie, Yves
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910050517254144
author Azzouz, Sofiane
Vuissoz, Pierre-André
Laprie, Yves
author_facet Azzouz, Sofiane
Vuissoz, Pierre-André
Laprie, Yves
contents Articulatory acoustic inversion reconstructs vocal tract shapes from speech. Real-time magnetic resonance imaging (rt-MRI) allows simultaneous acquisition of both the acoustic speech signal and articulatory information. Besides the complexity of rt-MRI acquisition, the recorded audio is heavily corrupted by scanner noise and requires denoising to be usable. For practical use, it must be possible to invert speech recorded without MRI noise. In this study, we investigate the use of speech recorded in a clean acoustic environment as an alternative to denoised MRI speech. To this end we compare two signals from the same speaker with identical sentences which are aligned using phonetic segmentation. A model trained on denoised MRI speech is evaluated on both denoised MRI and clean speech. We also assess a model trained and tested only on clean speech. Results show that clean speech supports articulatory inversion effectively, achieving an RMSE of 1.56 mm, close to MRI-based performance.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11845
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Acoustic-to-Articulatory Inversion of Clean Speech Using an MRI-Trained Model
Azzouz, Sofiane
Vuissoz, Pierre-André
Laprie, Yves
Audio and Speech Processing
Articulatory acoustic inversion reconstructs vocal tract shapes from speech. Real-time magnetic resonance imaging (rt-MRI) allows simultaneous acquisition of both the acoustic speech signal and articulatory information. Besides the complexity of rt-MRI acquisition, the recorded audio is heavily corrupted by scanner noise and requires denoising to be usable. For practical use, it must be possible to invert speech recorded without MRI noise. In this study, we investigate the use of speech recorded in a clean acoustic environment as an alternative to denoised MRI speech. To this end we compare two signals from the same speaker with identical sentences which are aligned using phonetic segmentation. A model trained on denoised MRI speech is evaluated on both denoised MRI and clean speech. We also assess a model trained and tested only on clean speech. Results show that clean speech supports articulatory inversion effectively, achieving an RMSE of 1.56 mm, close to MRI-based performance.
title Acoustic-to-Articulatory Inversion of Clean Speech Using an MRI-Trained Model
topic Audio and Speech Processing
url https://arxiv.org/abs/2603.11845