SNAC: Speaker-Normalized Affine Coupling Layer in Flow-Based Architecture for Zero-Shot Multi-Speaker Text-to-Speech

Author:

Choi Byoung Jin1ORCID,Jeong Myeonghun1ORCID,Lee Joun Yeop2,Kim Nam Soo1ORCID

Affiliation:

1. Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea

2. Samsung Research, Samsung Electronics Co., Ltd, Seoul, South Korea

Funder

Samsung Research

Samsung Electronics Co., Ltd.

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Electrical and Electronic Engineering,Signal Processing

Reference43 articles.

1. LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech

2. CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92;yamagishi,2019

3. Glow: Generative flow with invertible 1x1 convolutions;kingma;Proc Adv Neural Inf Process Syst,0

4. Density estimation using real NVP;dinh;Proc Int Conf Learn Representations,0

5. Nice: Non-linear independent components estimation;dinh;Proc Int Conf Mach Learn Workshop,0

Cited by 7 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Central Kurdish Text-to-Speech Synthesis with Novel End-to-End Transformer Training;Algorithms;2024-07-03

2. Optimizing feature fusion for improved zero-shot adaptation in text-to-speech synthesis;EURASIP Journal on Audio, Speech, and Music Processing;2024-05-28

3. Latent Filling: Latent Space Data Augmentation for Zero-Shot Speech Synthesis;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. Variable-Length Speaker Conditioning in Flow-Based Text-to-Speech;IEEE Signal Processing Letters;2024

5. Transfer Learning for Low-Resource, Multi-Lingual, and Zero-Shot Multi-Speaker Text-to-Speech;IEEE/ACM Transactions on Audio, Speech, and Language Processing;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3