OpenCodePapers
speech-synthesis-on-libritts
Accented Speech Recognition
Speech Synthesis
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
PESQ
↕
M-STFT
↕
MCD
↕
Periodicity
↕
V/UV F1
↕
ModelName
ReleaseDate
↕
Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization
✓ Link
4.454
0.7358
0.0528
0.9756
PeriodWave-Turbo-L
2024-08-15
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
✓ Link
4.362
0.7026
0.2903
0.0593
0.9793
BigVGAN-v2
2022-06-09
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks
✓ Link
4.3536
0.7982
0.0751
0.9745
EVA-GAN-big
2024-01-31
PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation
✓ Link
4.248
1.0269
0.0765
0.9651
PeriodWave + FreeU
2024-08-14
RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction
✓ Link
4.228
0.090
0.968
RFWave
2024-03-08
BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network
✓ Link
4.120
0.7992
0.4129
0.0924
0.9644
BigVSAN (w/ snakebeta)
2023-09-06
BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network
✓ Link
4.116
0.7881
0.3381
0.0935
0.9635
BigVSAN
2023-09-06
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks
✓ Link
4.0330
0.9485
0.0942
0.9658
EVA-GAN-base
2024-01-31
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
✓ Link
4.027
0.7997
0.3745
0.1018
0.9598
BigVGAN
2022-06-09
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
✓ Link
3.70
0.101
0.9582
Vocos
2023-06-01
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
✓ Link
3.519
0.8788
0.4564
0.1287
0.9459
BigVGAN-base
2022-06-09
WaveGlow: A Flow-based Generative Network for Speech Synthesis
✓ Link
3.138
1.3099
2.3591
0.1485
0.9378
WaveGlow
2018-10-31
WaveFlow: A Compact Flow-based Model for Raw Audio
✓ Link
3.027
1.1120
1.2455
0.1416
0.9410
WaveFlow
2019-12-03
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
✓ Link
2.947
1.0017
0.6603
0.1565
0.9300
HiFi-GAN
2020-10-12
Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions
✓ Link
1.701
2.2358
1.8854
0.3044
0.8144
SC-WaveRNN
2020-08-09