Tag
This paper proposes a classifier-based framework to audit multilingual TTS systems for phonological faithfulness, using Assamese ATR vowel harmony as a case study. It reveals that Meta's MMS TTS frequently misproduces advanced tongue root vowels, a bias absent in human speech.
UR-BERT proposes a Romanized transcription-based text encoder for massively multilingual TTS, scaling to 495 languages by using universal Romanization and a speech token prediction objective to enhance phonetic alignment and generalization to unseen languages.