RedPen: Region- and Reason-Annotated Dataset of Unnatural Speech
This provides a more interpretable evaluation method for speech synthesis researchers, though it is incremental as it builds on existing MOS-based evaluation.
The authors tackled the problem of evaluating speech synthesis models by creating RedPen, a dataset with 180 synthesized speeches annotated for unnatural regions and error types, which better explains unnatural speech than model-driven predictions.
Even with recent advances in speech synthesis models, the evaluation of such models is based purely on human judgement as a single naturalness score, such as the Mean Opinion Score (MOS). The score-based metric does not give any further information about which parts of speech are unnatural or why human judges believe they are unnatural. We present a novel speech dataset, RedPen, with human annotations on unnatural speech regions and their corresponding reasons. RedPen consists of 180 synthesized speeches with unnatural regions annotated by crowd workers; These regions are then reasoned and categorized by error types, such as voice trembling and background noise. We find that our dataset shows a better explanation for unnatural speech regions than the model-driven unnaturalness prediction. Our analysis also shows that each model includes different types of error types. Summing up, our dataset successfully shows the possibility that various error regions and types lie under the single naturalness score. We believe that our dataset will shed light on the evaluation and development of more interpretable speech models in the future. Our dataset will be publicly available upon acceptance.