Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Speech Synthesis on LibriSpeech benchmark leaderboard · SOTA2 Research

Research Benchmarks

Speech Synthesis on LibriSpeech

0.67CMOS-N ScoreVall-E

Updated 5mo ago

Evaluation Results

Method	Links
Vall-E2023.06		0.67	-0.47

SOTA Paper

Vall-E

Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Dataset

LibriSpeech

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Text-to-Speech on LibriTTS clean (test)Zero-shot speaker adaptation on LibriTTS clean (test)Speech Synthesis on LJSpeech (CMOS-N)Speech Synthesis on VCTK