Speech Recognition on LibriTTS

Metric: PESQ (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	PESQ▼	Extra Data	Paper	Date↕	Code
1	PeriodWave-Turbo-L	4.454	No	Accelerating High-Fidelity Waveform Generation v...	2024-08-15	Code
2	BigVGAN-v2	4.362	Yes	BigVGAN: A Universal Neural Vocoder with Large-S...	2022-06-09	Code
3	EVA-GAN-big	4.3536	Yes	EVA-GAN: Enhanced Various Audio Generation via S...	2024-01-31	Code
4	PeriodWave + FreeU	4.248	No	PeriodWave: Multi-Period Flow Matching for High-...	2024-08-14	Code
5	RFWave	4.228	No	RFWave: Multi-band Rectified Flow for Audio Wave...	2024-03-08	Code
6	BigVSAN (w/ snakebeta)	4.12	No	BigVSAN: Enhancing GAN-based Neural Vocoders wit...	2023-09-06	Code
7	BigVSAN	4.116	No	BigVSAN: Enhancing GAN-based Neural Vocoders wit...	2023-09-06	Code
8	EVA-GAN-base	4.033	Yes	EVA-GAN: Enhanced Various Audio Generation via S...	2024-01-31	Code
9	BigVGAN	4.027	No	BigVGAN: A Universal Neural Vocoder with Large-S...	2022-06-09	Code
10	Vocos	3.7	No	Vocos: Closing the gap between time-domain and F...	2023-06-01	Code
11	BigVGAN-base	3.519	No	BigVGAN: A Universal Neural Vocoder with Large-S...	2022-06-09	Code
12	WaveGlow	3.138	No	WaveGlow: A Flow-based Generative Network for Sp...	2018-10-31	Code
13	WaveFlow	3.027	No	WaveFlow: A Compact Flow-based Model for Raw Audio	2019-12-03	Code
14	HiFi-GAN	2.947	No	HiFi-GAN: Generative Adversarial Networks for Ef...	2020-10-12	Code
15	SC-WaveRNN	1.701	No	Speaker Conditional WaveRNN: Towards Universal N...	2020-08-09	Code

#1PeriodWave-Turbo-LSOTA
4.454
PESQ· 2024-08-15
Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization Code
#2BigVGAN-v2SOTA
4.362
PESQ· Extra Data· 2022-06-09
BigVGAN: A Universal Neural Vocoder with Large-Scale Training Code
#3EVA-GAN-big
4.3536
PESQ· Extra Data· 2024-01-31
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks Code
#4PeriodWave + FreeU
4.248
PESQ· 2024-08-14
PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation Code
#5RFWave
4.228
PESQ· 2024-03-08
RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction Code
#6BigVSAN (w/ snakebeta)
4.12
PESQ· 2023-09-06
BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network Code
#7BigVSAN
4.116
PESQ· 2023-09-06
BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network Code
#8EVA-GAN-base
4.033
PESQ· Extra Data· 2024-01-31
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks Code
#9BigVGAN
4.027
PESQ· 2022-06-09
BigVGAN: A Universal Neural Vocoder with Large-Scale Training Code
#10Vocos
3.7
PESQ· 2023-06-01
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis Code
#11BigVGAN-base
3.519
PESQ· 2022-06-09
BigVGAN: A Universal Neural Vocoder with Large-Scale Training Code
#12WaveGlowSOTA
3.138
PESQ· 2018-10-31
WaveGlow: A Flow-based Generative Network for Speech Synthesis Code
#13WaveFlow
3.027
PESQ· 2019-12-03
WaveFlow: A Compact Flow-based Model for Raw Audio Code
#14HiFi-GAN
2.947
PESQ· 2020-10-12
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis Code
#15SC-WaveRNN
1.701
PESQ· 2020-08-09
Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions Code