MHTTS: Fast multi-head text-to-speech for spontaneous speech with imperfect transcription.

Dabiao Ma Zhiba Su Yitong Zhang Meng Li Feng Ye

Published in: CoRR (2022)

Keyphrases

prosodic features
text to speech
spontaneous speech
automatic transcription
human machine interaction
speech synthesis
spoken language
automatic speech recognition
speaker verification
programming tool
word processing
text to speech synthesis
gesture recognition
spoken document retrieval
pattern recognition