Affectron: Emotional Speech Synthesis with Affective and Contextually Aligned Nonverbal Vocalizations

TL;DR

Affectron is a framework for generating expressive, contextually aligned nonverbal vocalizations in emotional speech synthesis, overcoming data limitations with novel training strategies.

Contribution

It introduces an NV-augmented training strategy and NV structural masking to improve diversity and naturalness in NV generation from limited data.

Findings

Affectron produces more expressive NVs than baselines.

It maintains naturalness of verbal speech while adding NVs.

The approach enhances diversity and contextual alignment of NVs.

Abstract

Nonverbal vocalizations (NVs), such as laughter and sighs, are central to the expression of affective cues in emotional speech synthesis. However, learning diverse and contextually aligned NVs remains challenging in open settings due to limited NV data and the lack of explicit supervision. Motivated by this challenge, we propose Affectron as a framework for affective and contextually aligned NV generation. Built on a small-scale open and decoupled corpus, Affectron introduces an NV-augmented training strategy that expands the distribution of NV types and insertion locations. We further incorporate NV structural masking into a speech backbone pre-trained on purely verbal speech to enable diverse and natural NV synthesis. Experimental results demonstrate that Affectron produces more expressive and diverse NVs than baseline systems while preserving the naturalness of the verbal speech stream.