A Preliminary Study on Wav2Vec 2.0 Embeddings for Text-to-Speech.

Yohan Lim Namhyeong Kim Seung Yun Sang-Hun Kim Seung-Ik Lee

Published in: ICTC (2021)

Keyphrases

text to speech
speech synthesis
programming tool
vector space
euclidean space
word processing
prosodic features
text to speech synthesis
manifold learning
english text
dimensionality reduction
low dimensional
hilbert space
web applications
distance measure
multi modal