HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Text To Speech Synthesis On Ljspeech

評価指標

Audio Quality MOS

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Audio Quality MOS
Paper TitleRepository
FastSpeech (Mel + WaveGlow)3.84FastSpeech: Fast, Robust and Controllable Text to Speech
FastDiff-TTS4.03FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis
FastSpeech 2 + HiFiGAN4.34NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
Grad-TTS + HiFiGAN (1000 steps)4.37Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech-
Flowtron-Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
Transformer TTS (Mel + WaveGlow)3.88Neural Speech Synthesis with Transformer Network
VITS4.43NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
Matcha-TTS-Matcha-TTS: A fast TTS architecture with conditional flow matching
Tacotron 2-Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
FastSpeech 2 + HiFiGAN4.32FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
temp1.25--
FastDiff (4 steps)4.28FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis
OverFlow3.37OverFlow: Putting flows on top of neural transducers for better TTS
NaturalSpeech4.56NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
Merlin2.4FastSpeech: Fast, Robust and Controllable Text to Speech
Glow-TTS + HiFiGAN4.34Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
0 of 16 row(s) selected.