|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM367316056 |
| 003 |
DE-627 |
| 005 |
20250103231833.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240120s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2024.3356232
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1650.xml
|
| 035 |
|
|
|a (DE-627)NLM367316056
|
| 035 |
|
|
|a (NLM)38241115
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Tan, Xu
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a NaturalSpeech
|b End-to-End Text-to-Speech Synthesis With Human-Level Quality
|
| 264 |
|
1 |
|c 2024
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 07.05.2024
|
| 500 |
|
|
|a Date Revised 03.01.2025
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status MEDLINE
|
| 520 |
|
|
|a Text-to-speech (TTS) has made rapid progress in both academia and industry in recent years. Some questions naturally arise that whether a TTS system can achieve human-level quality, how to define/judge that quality, and how to achieve it. In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on benchmark datasets. Specifically, we leverage a variational auto-encoder (VAE) for end-to-end text-to-waveform generation, with several key modules to enhance the capacity of the prior from text and reduce the complexity of the posterior from speech, including phoneme pre-training, differentiable duration modeling, bidirectional prior/posterior modeling, and a memory mechanism in VAE. Experimental evaluations on the popular LJSpeech dataset show that our proposed NaturalSpeech achieves -0.01 CMOS (comparative mean opinion score) to human recordings at the sentence level, with Wilcoxon signed rank test at p-level p >> 0.05, which demonstrates no statistically significant difference from human recordings for the first time
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, Non-U.S. Gov't
|
| 650 |
|
4 |
|a Research Support, U.S. Gov't, Non-P.H.S.
|
| 700 |
1 |
|
|a Chen, Jiawei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Haohe
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Cong, Jian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Chen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Yanqing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Xi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Leng, Yichong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yi, Yuanhao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a He, Lei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhao, Sheng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Qin, Tao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Soong, Frank
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Tie-Yan
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 46(2024), 6 vom: 22. Juni, Seite 4234-4245
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:6
|g day:22
|g month:06
|g pages:4234-4245
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3356232
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 46
|j 2024
|e 6
|b 22
|c 06
|h 4234-4245
|