FlashSpeech: Efficient Zero-Shot Speech Synthesis#Generative Speech#Machine Learning#Audio#Paper#PDF·arxiv.org·Apr 24, 2024FlashSpeech: Efficient Zero-Shot Speech Synthesis
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised TrainingPDF#Machine Learning#Audio#Paper#PDF·arxiv.org·Jun 4, 2023MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training