Multi-view Temporal Alignment for Non-parallel Articulatory-to-Acoustic Speech Synthesis

TL;DR

This paper introduces a multi-view learning approach for articulatory-to-acoustic speech synthesis that aligns non-parallel data, enabling speech generation without the need for synchronized training pairs.

Contribution

It proposes a novel algorithm that aligns non-parallel articulatory and acoustic sequences using a shared latent space and dynamic time warping, expanding A2A synthesis applicability.

Findings

Speech quality in non-aligned data is comparable to aligned data.

The method effectively finds optimal temporal alignments.

Multiple variants of the alignment approach are explored.

Abstract

Articulatory-to-acoustic (A2A) synthesis refers to the generation of audible speech from captured movement of the speech articulators. This technique has numerous applications, such as restoring oral communication to people who cannot longer speak due to illness or injury. Most successful techniques so far adopt a supervised learning framework, in which time-synchronous articulatory-and-speech recordings are used to train a supervised machine learning algorithm that can be used later to map articulator movements to speech. This, however, prevents the application of A2A techniques in cases where parallel data is unavailable, e.g., a person has already lost her/his voice and only articulatory data can be captured. In this work, we propose a solution to this problem based on the theory of multi-view learning. The proposed algorithm attempts to find an optimal temporal alignment between pairs of non-aligned articulatory-and-acoustic sequences with the same phonetic content by projecting them into a common latent space where both views are maximally correlated and then applying dynamic time warping. Several variants of this idea are discussed and explored. We show that the quality of speech generated in the non-aligned scenario is comparable to that obtained in the parallel scenario.