Reconstructing Speech from Real-Time Articulatory MRI Using Neural Vocoders

TL;DR

This paper explores reconstructing speech from real-time MRI of articulators using neural vocoders, demonstrating promising results in spectral shape recovery but highlighting the need for further refinement.

Contribution

It introduces a neural network-based method to reconstruct speech from MRI data using spectral vector estimation and neural vocoders, a novel approach in this domain.

Findings

Successfully reconstructs gross spectral shape of speech

Neural architectures outperform baseline in spectral estimation

Further improvements needed for fine spectral detail reproduction

Abstract

Several approaches exist for the recording of articulatory movements, such as eletromagnetic and permanent magnetic articulagraphy, ultrasound tongue imaging and surface electromyography. Although magnetic resonance imaging (MRI) is more costly than the above approaches, the recent developments in this area now allow the recording of real-time MRI videos of the articulators with an acceptable resolution. Here, we experiment with the reconstruction of the speech signal from a real-time MRI recording using deep neural networks. Instead of estimating speech directly, our networks are trained to output a spectral vector, from which we reconstruct the speech signal using the WaveGlow neural vocoder. We compare the performance of three deep neural architectures for the estimation task, combining convolutional (CNN) and recurrence-based (LSTM) neural layers. Besides the mean absolute error (MAE) of our networks, we also evaluate our models by comparing the speech signals obtained using several objective speech quality metrics like the mean cepstral distortion (MCD), Short-Time Objective Intelligibility (STOI), Perceptual Evaluation of Speech Quality (PESQ) and Signal-to-Distortion Ratio (SDR). The results indicate that our approach can successfully reconstruct the gross spectral shape, but more improvements are needed to reproduce the fine spectral details.