Topic
tts
Artificial Intelligence #flow-matching#tts
FlowEdit: Associative Memory Framework Cuts TTS Pronunciation Errors by 92.7% Without Retraining
FlowEdit, a new lifelong adaptation framework for flow-matching text-to-speech systems, corrects pronunciation errors on out-of-vocabulary proper nouns without retraining. By storing corrections as latent edits in a Modern Hopfield Network, it achieves a 92.7% reduction in Phoneme Error Rate on 312 multilingual proper nouns while maintaining speech quality.
Jun 22, 2026 1 source
Artificial Intelligence #zero-shot#tts
ZeSTA Framework Enhances Zero-Shot TTS Augmentation for Data-Efficient Personalized Speech Synthesis
Researchers propose ZeSTA, a domain-conditioned training framework that distinguishes real and synthetic speech via a lightweight domain embedding, combined with real-data oversampling. The approach improves speaker similarity over naive synthetic augmentation while preserving intelligibility and perceptual quality in low-resource personalized speech synthesis.
Jun 20, 2026 1 source