Pathological voice adaptation with autoencoder-based voice conversion

TL;DR

This paper introduces a novel pathological speech synthesis method that customizes existing pathological speech samples to new speakers using autoencoder-based voice conversion, improving naturalness and speaker characteristic transfer.

Contribution

It presents a new approach that simplifies pathological speech conversion by focusing on speaker change rather than speech degradation, validated with a proof of concept using dysarthric speech.

Findings

Reasonable naturalness for high intelligibility speakers

Successful speaker characteristic conversion for low and high intelligibility speakers

Lower intelligibility speakers show marginal naturalness degradation

Abstract

In this paper, we propose a new approach to pathological speech synthesis. Instead of using healthy speech as a source, we customise an existing pathological speech sample to a new speaker's voice characteristics. This approach alleviates the evaluation problem one normally has when converting typical speech to pathological speech, as in our approach, the voice conversion (VC) model does not need to be optimised for speech degradation but only for the speaker change. This change in the optimisation ensures that any degradation found in naturalness is due to the conversion process and not due to the model exaggerating characteristics of a speech pathology. To show a proof of concept of this method, we convert dysarthric speech using the UASpeech database and an autoencoder-based VC technique. Subjective evaluation results show reasonable naturalness for high intelligibility dysarthric speakers, though lower intelligibility seems to introduce a marginal degradation in naturalness scores for mid and low intelligibility speakers compared to ground truth. Conversion of speaker characteristics for low and high intelligibility speakers is successful, but not for mid. Whether the differences in the results for the different intelligibility levels is due to the intelligibility levels or due to the speakers needs to be further investigated.