SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion.

Bingsong Bai Fengping Wang Yingming Gao Ya Li

Published in: CoRR (2024)

Keyphrases

fundamental frequency
acoustic features
scalable video coding
low complexity
music information retrieval
bitstream
data sets
mpeg avc
video transmission
neural network
emotion recognition
case study
bit rate
feature vectors
text to speech
computer vision
genetic algorithm
voice and data services