IEEE - Institute of Electrical and Electronics Engineers, Inc. - Semi-supervised Training for Improving Data Efficiency in End-to-end Speech Synthesis

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Author(s): Yu-An Chung ; Yuxuan Wang ; Wei-Ning Hsu ; Yu Zhang ; R.J. Skerry-Ryan
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 May 2019
Conference Location: Brighton, United Kingdom, United Kingdom
Conference Date: 12 May 2019
Page(s): 6,940 - 6,944
ISBN (Electronic): 978-1-4799-8131-1
ISSN (Electronic): 2379-190X
DOI: 10.1109/ICASSP.2019.8683862
Regular:

Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <;text, audio> pairs for training, which... View More

Advertisement