Real-Time MRI Video synthesis from time aligned phonemes with sequence-to-sequence networks

TL;DR

This paper introduces a sequence-to-sequence transformer-based model with CVAE features to generate realistic real-time MRI videos from phoneme sequences, aiding speech production research.

Contribution

It presents a novel model combining transformers and CVAE for subject-specific rtMRI video synthesis from phonemes, improving realism and generalization.

Findings

Model generates realistic rtMRI videos for unseen utterances.

Adding CVAE improves learning in difficult subject-specific mappings.

Subject-specific training enhances synthesis accuracy.

Abstract

Real-Time Magnetic resonance imaging (rtMRI) of the midsagittal plane of the mouth is of interest for speech production research. In this work, we focus on estimating utterance level rtMRI video from the spoken phoneme sequence. We obtain time-aligned phonemes from forced alignment, to obtain frame-level phoneme sequences which are aligned with rtMRI frames. We propose a sequence-to-sequence learning model with a transformer phoneme encoder and convolutional frame decoder. We then modify the learning by using intermediary features obtained from sampling from a pretrained phoneme-conditioned variational autoencoder (CVAE). We train on 8 subjects in a subject-specific manner and demonstrate the performance with a subjective test. We also use an auxiliary task of air tissue boundary (ATB) segmentation to obtain the objective scores on the proposed models. We show that the proposed method is able to generate realistic rtMRI video for unseen utterances, and adding CVAE is beneficial for learning the sequence-to-sequence mapping for subjects where the mapping is hard to learn.