2022
Improving Phonetic Realizations in its by Using Phoneme-Aligned Graphemes
ICASSP 2022accepted
Most text-to-speech acoustic models, such as WaveNet, Tacotron, ClariNet, etc., use either a phoneme sequence or a letter sequence as the fundamental unit of speech. Although the letter (or grapheme) sequence closely matches the actual runtime input of the TTS system, it often fails to represent the…