audio-7
Text-To-Speech Synthesis
3260 papers • 126 benchmarks • 313 datasets
Text-To-Speech Synthesis is a machine learning task that involves converting written text into spoken words. The goal is to generate synthetic speech that sounds natural and resembles human speech as closely as possible.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in text-to-speech-synthesis-23
Trend
Dataset
Best Model
Actions
LJSpeech
LJSpeech
CMUDict 0.7b
CMUDict 0.7b
20000 utterances
20000 utterances
Libraries
iUse these libraries to find text-to-speech-synthesis-23 models and implementations
12 papers 9,288
Datasets
Subtasks
Most implemented papers
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
Tao Qin, Tie-Yan Liu, Zhou Zhao, Xu Tan, Yi Ren, Sheng Zhao, Chenxu Hu•Sun Jun 07 2020
FastSpeech 2 is proposed, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by directly training the model with ground-truth target instead of the simplified output from teacher, and introducing more variation information of speech as conditional inputs.
1659
