AI RESEARCH
TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis
arXiv CS.CL
•
ArXi:2604.22225v1 Announce Type: new While generative text-to-speech (TTS) models approach human-level quality, monolithic metrics fail to diagnose fine-grained acoustic artifacts or explain perceptual collapse. To address this, we propose TTS-PRISM, a multi-dimensional diagnostic framework for Mandarin. First, we establish a 12-dimensional schema spanning stability to advanced expressiveness. Second, we design a targeted synthesis pipeline with adversarial perturbations and expert anchors to build a high-quality diagnostic dataset.