A Multimodal Real-Time MRI Articulatory Corpus of French for Speech Research

Abstract

In this work we describe the creation of ArtSpeechMRIfr: a real-time as well as static magnetic resonance imaging (rtMRI, 3D MRI) database of the vocal tract. The database contains also processed data: denoised audio, its phonetically aligned annotation, articulatory contours, and vocal tract volume information, which provides a rich resource for speech research. The database is built on data from two male speakers of French. It covers a number of phonetic contexts in the controlled part, as well as spontaneous speech, 3D MRI scans of sustained vocalic articulations, and of the dental casts of the subjects. The corpus for rtMRI consists of 79 synthetic sentences constructed from a phonetized dictionary that makes possible to shorten the duration of acquisitions while keeping a very good coverage of the phonetic contexts which exist in French. The 3D MRI includes acquisitions for 12 French vowels and 10 consonants, each of which was pronounced in several vocalic contexts. Articulatory contours (tongue, jaw, epiglottis, larynx, velum, lips) as well as 3D volumes were manually drawn for a part of the images.

Automatic generation of the complete vocal tract shape from the sequence of phonemes to be articulated

“…Along with this work, we extend the research to a larger dataset than that used in [23]. The dataset [24] is composed of one male French native speaker. The MRI sequences were recorded at Max Plank Institute, Göttingen, Germany.…”

Autoencoder-Based Tongue Shape Estimation During Continuous Speech

“…The dataset [13] is the same used in [9] , y) coordinates of the 50 samples in the articulator's curve and were extracted using the procedure described in [9]. The phonetic annotations were extracted using forced alignment [14] and then corrected by a specialist in phonetics.…”