A Human-in-the-Loop Approach to Improving Cross-Text Prosody Transfer
This addresses a specific bottleneck in TTS prosody transfer for applications requiring varied and natural speech synthesis, but it is incremental as it builds on existing transfer models with human intervention.
The paper tackles the problem of cross-text prosody transfer in Text-To-Speech models, where models struggle to separate prosody from text when reference and target texts differ, leading to reduced naturalness. The proposed Human-in-the-Loop approach allows users to adjust prosody, resulting in renditions that maintain reference prosody while being rated as more appropriate for the target text 57.8% of the time.
Text-To-Speech (TTS) prosody transfer models can generate varied prosodic renditions, for the same text, by conditioning on a reference utterance. These models are trained with a reference that is identical to the target utterance. But when the reference utterance differs from the target text, as in cross-text prosody transfer, these models struggle to separate prosody from text, resulting in reduced perceived naturalness. To address this, we propose a Human-in-the-Loop (HitL) approach. HitL users adjust salient correlates of prosody to make the prosody more appropriate for the target text, while maintaining the overall reference prosodic effect. Human adjusted renditions maintain the reference prosody while being rated as more appropriate for the target text $57.8\%$ of the time. Our analysis suggests that limited user effort suffices for these improvements, and that closeness in the latent reference space is not a reliable prosodic similarity metric for the cross-text condition.