paper-with-me

Speech Synthesis 벤치마크

Speech Synthesis on North American English

21개 결과 · ⬇ CSV · JSON

Mean Opinion Score

0 1.131 2.263 3.394 4.526 2016-09 2026-09 WaveNet (L+F) — 4.21 (2016-09-12) HMM-driven concatenative — 3.86 (2016-09-12) LSTM-RNN parametric — 3.67 (2016-09-12) WaveNet (L+F) — 4.21 (2016-09-12) HMM-driven concatenative — 3.86 (2016-09-12) LSTM-RNN parametric — 3.67 (2016-09-12) WaveNet (L+F) — 4.21 (2016-09-12) HMM-driven concatenative — 3.86 (2016-09-12) LSTM-RNN parametric — 3.67 (2016-09-12) Tacotron — 4.001 (2017-03-29) Tacotron — 4.001 (2017-03-29) Tacotron — 4.001 (2017-03-29) Tacotron 2 — 4.526 (2017-12-16) WaveNet (Linguistic) — 4.341 (2017-12-16) Tacotron 2 — 4.526 (2017-12-16) WaveNet (Linguistic) — 4.341 (2017-12-16) Tacotron 2 — 4.526 (2017-12-16) WaveNet (Linguistic) — 4.341 (2017-12-16) means — 0.0 (2017-12-23) means — 0.0 (2017-12-23) means — 0.0 (2017-12-23) WaveNet (L+F) — 4.21 (2016-09-12) Tacotron 2 — 4.526 (2017-12-16)
RankModel Mean Opinion Score PaperCodeYear
1 Tacotron 2 4.526 Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions coqui-ai/TTS · PaddlePaddle/PaddleSpeech · NVIDIA/tacotron2 · +30 2017
2 WaveNet (Linguistic) 4.341 Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions coqui-ai/TTS · PaddlePaddle/PaddleSpeech · NVIDIA/tacotron2 · +30 2017
3 WaveNet (L+F) 4.21 WaveNet: A Generative Model for Raw Audio ibab/tensorflow-wavenet · awslabs/gluon-ts · karpathy/makemore · +59 2016
4 Tacotron 4.001 Tacotron: Towards End-to-End Speech Synthesis CorentinJ/Real-Time-Voice-Cloning · coqui-ai/TTS · PaddlePaddle/PaddleSpeech · +27 2017
5 HMM-driven concatenative 3.86 WaveNet: A Generative Model for Raw Audio ibab/tensorflow-wavenet · awslabs/gluon-ts · karpathy/makemore · +59 2016
6 LSTM-RNN parametric 3.67 WaveNet: A Generative Model for Raw Audio ibab/tensorflow-wavenet · awslabs/gluon-ts · karpathy/makemore · +59 2016
7 means 0 Merging $K$-means with hierarchical clustering for identifying general-shaped groups 2017
8 Tacotron 2 4.526 Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions coqui-ai/TTS · PaddlePaddle/PaddleSpeech · NVIDIA/tacotron2 · +30 2017
9 WaveNet (Linguistic) 4.341 Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions coqui-ai/TTS · PaddlePaddle/PaddleSpeech · NVIDIA/tacotron2 · +30 2017
10 WaveNet (L+F) 4.21 WaveNet: A Generative Model for Raw Audio ibab/tensorflow-wavenet · awslabs/gluon-ts · karpathy/makemore · +59 2016
11 Tacotron 4.001 Tacotron: Towards End-to-End Speech Synthesis CorentinJ/Real-Time-Voice-Cloning · coqui-ai/TTS · PaddlePaddle/PaddleSpeech · +27 2017
12 HMM-driven concatenative 3.86 WaveNet: A Generative Model for Raw Audio ibab/tensorflow-wavenet · awslabs/gluon-ts · karpathy/makemore · +59 2016
13 LSTM-RNN parametric 3.67 WaveNet: A Generative Model for Raw Audio ibab/tensorflow-wavenet · awslabs/gluon-ts · karpathy/makemore · +59 2016
14 means 0 Merging $K$-means with hierarchical clustering for identifying general-shaped groups 2017
15 Tacotron 2 4.526 Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions coqui-ai/TTS · PaddlePaddle/PaddleSpeech · NVIDIA/tacotron2 · +30 2017
16 WaveNet (Linguistic) 4.341 Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions coqui-ai/TTS · PaddlePaddle/PaddleSpeech · NVIDIA/tacotron2 · +30 2017
17 WaveNet (L+F) 4.21 WaveNet: A Generative Model for Raw Audio ibab/tensorflow-wavenet · awslabs/gluon-ts · karpathy/makemore · +59 2016
18 Tacotron 4.001 Tacotron: Towards End-to-End Speech Synthesis CorentinJ/Real-Time-Voice-Cloning · coqui-ai/TTS · PaddlePaddle/PaddleSpeech · +27 2017
19 HMM-driven concatenative 3.86 WaveNet: A Generative Model for Raw Audio ibab/tensorflow-wavenet · awslabs/gluon-ts · karpathy/makemore · +59 2016
20 LSTM-RNN parametric 3.67 WaveNet: A Generative Model for Raw Audio ibab/tensorflow-wavenet · awslabs/gluon-ts · karpathy/makemore · +59 2016
1–20 / 21 다음 → 페이지당 10 20 50 100