Accented Speech Recognition on LibriTTS

Metric: M-STFT (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	M-STFT▼	Extra Data	Paper	Date↕	Code
1	SC-WaveRNN	2.2358	No	Speaker Conditional WaveRNN: Towards Universal N...	2020-08-09	Code
2	WaveGlow	1.3099	No	WaveGlow: A Flow-based Generative Network for Sp...	2018-10-31	Code
3	WaveFlow	1.112	No	WaveFlow: A Compact Flow-based Model for Raw Audio	2019-12-03	Code
4	PeriodWave + FreeU	1.0269	No	PeriodWave: Multi-Period Flow Matching for High-...	2024-08-14	Code
5	HiFi-GAN	1.0017	No	HiFi-GAN: Generative Adversarial Networks for Ef...	2020-10-12	Code
6	EVA-GAN-base	0.9485	Yes	EVA-GAN: Enhanced Various Audio Generation via S...	2024-01-31	Code
7	BigVGAN-base	0.8788	No	BigVGAN: A Universal Neural Vocoder with Large-S...	2022-06-09	Code
8	BigVGAN	0.7997	No	BigVGAN: A Universal Neural Vocoder with Large-S...	2022-06-09	Code
9	BigVSAN (w/ snakebeta)	0.7992	No	BigVSAN: Enhancing GAN-based Neural Vocoders wit...	2023-09-06	Code
10	EVA-GAN-big	0.7982	Yes	EVA-GAN: Enhanced Various Audio Generation via S...	2024-01-31	Code
11	BigVSAN	0.7881	No	BigVSAN: Enhancing GAN-based Neural Vocoders wit...	2023-09-06	Code
12	PeriodWave-Turbo-L	0.7358	No	Accelerating High-Fidelity Waveform Generation v...	2024-08-15	Code
13	BigVGAN-v2	0.7026	Yes	BigVGAN: A Universal Neural Vocoder with Large-S...	2022-06-09	Code

#1SC-WaveRNNSOTA
2.2358
M-STFT· 2020-08-09
Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions Code
#2WaveGlowSOTA
1.3099
M-STFT· 2018-10-31
WaveGlow: A Flow-based Generative Network for Speech Synthesis Code
#3WaveFlow
1.112
M-STFT· 2019-12-03
WaveFlow: A Compact Flow-based Model for Raw Audio Code
#4PeriodWave + FreeU
1.0269
M-STFT· 2024-08-14
PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation Code
#5HiFi-GAN
1.0017
M-STFT· 2020-10-12
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis Code
#6EVA-GAN-base
0.9485
M-STFT· Extra Data· 2024-01-31
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks Code
#7BigVGAN-base
0.8788
M-STFT· 2022-06-09
BigVGAN: A Universal Neural Vocoder with Large-Scale Training Code
#8BigVGAN
0.7997
M-STFT· 2022-06-09
BigVGAN: A Universal Neural Vocoder with Large-Scale Training Code
#9BigVSAN (w/ snakebeta)
0.7992
M-STFT· 2023-09-06
BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network Code
#10EVA-GAN-big
0.7982
M-STFT· Extra Data· 2024-01-31
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks Code
#11BigVSAN
0.7881
M-STFT· 2023-09-06
BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network Code
#12PeriodWave-Turbo-L
0.7358
M-STFT· 2024-08-15
Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization Code
#13BigVGAN-v2
0.7026
M-STFT· Extra Data· 2022-06-09
BigVGAN: A Universal Neural Vocoder with Large-Scale Training Code