Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data

10.1109/TASLP.2021.3066047

Saved in:
Bibliographic Details
Main Author: Li, Haizhou
Other Authors: BUILDING
Format: Article
Language:English
Published: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC 2021
Subjects:
Online Access:https://scholarbank.nus.edu.sg/handle/10635/191976
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: National University of Singapore
Language: English
id sg-nus-scholar.10635-191976
record_format dspace
spelling sg-nus-scholar.10635-1919762024-04-25T03:36:46Z Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data Li, Haizhou BUILDING ELECTRICAL AND COMPUTER ENGINEERING Science & Technology Technology Acoustics Engineering, Electrical & Electronic Engineering Linguistics Decoding Transfer learning Training data Training Encoding Speech synthesis Autoencoder context vector non-parallel text -to-speech (TTS) transfer learning voice conversion (VC) TEXT-TO-SPEECH SPARSE REPRESENTATION ADAPTATION 10.1109/TASLP.2021.3066047 IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 29 1290-1302 completed 2021-06-11T08:17:04Z 2021-06-11T08:17:04Z 2021-01-01 2021-06-07T08:19:39Z Article Li, Haizhou (2021-01-01). Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 29 : 1290-1302. ScholarBank@NUS Repository. https://doi.org/10.1109/TASLP.2021.3066047 2329-9290 2329-9304 https://scholarbank.nus.edu.sg/handle/10635/191976 en IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC Elements
institution National University of Singapore
building NUS Library
continent Asia
country Singapore
Singapore
content_provider NUS Library
collection ScholarBank@NUS
language English
topic Science & Technology
Technology
Acoustics
Engineering, Electrical & Electronic
Engineering
Linguistics
Decoding
Transfer learning
Training data
Training
Encoding
Speech synthesis
Autoencoder
context vector
non-parallel
text -to-speech (TTS)
transfer learning
voice conversion (VC)
TEXT-TO-SPEECH
SPARSE REPRESENTATION
ADAPTATION
spellingShingle Science & Technology
Technology
Acoustics
Engineering, Electrical & Electronic
Engineering
Linguistics
Decoding
Transfer learning
Training data
Training
Encoding
Speech synthesis
Autoencoder
context vector
non-parallel
text -to-speech (TTS)
transfer learning
voice conversion (VC)
TEXT-TO-SPEECH
SPARSE REPRESENTATION
ADAPTATION
Li, Haizhou
Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data
description 10.1109/TASLP.2021.3066047
author2 BUILDING
author_facet BUILDING
Li, Haizhou
format Article
author Li, Haizhou
author_sort Li, Haizhou
title Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data
title_short Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data
title_full Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data
title_fullStr Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data
title_full_unstemmed Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data
title_sort transfer learning from speech synthesis to voice conversion with non-parallel training data
publisher IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
publishDate 2021
url https://scholarbank.nus.edu.sg/handle/10635/191976
_version_ 1800914824215920640