Speaker Identification on VoxCeleb1

Metric: Top-1 (%) (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	Top-1 (%)▼	Extra Data	Paper	Date↕	Code
1	MSM-MAE	96.6	Yes	Masked Modeling Duo: Towards a Universal Audio P...	2024-04-09	Code
2	M2D/0.6	96.5	Yes	Masked Modeling Duo: Towards a Universal Audio P...	2024-04-09	Code
3	M2D/0.7	96.3	Yes	Masked Modeling Duo: Towards a Universal Audio P...	2024-04-09	Code
4	AudioMAE (local)	94.8	Yes	Masked Autoencoders that Listen	2022-07-13	Code
5	M2D ratio=0.6	94.8	Yes	Masked Modeling Duo: Learning Representations by...	2022-10-26	Code
6	ATST Base (ours)	94.3	Yes	ATST: Audio Representation Learning with Teacher...	2022-04-26	Code
7	AudioMAE (global)	94.1	Yes	Masked Autoencoders that Listen	2022-07-13	Code
8	AutoSpeech (N=8,C=128)	87.66	Yes	AutoSpeech: Neural Architecture Search for Speak...	2020-05-07	Code
9	SSAST-FRAME	80.8	Yes	SSAST: Self-Supervised Audio Spectrogram Transfo...	2021-10-19	Code
10	SSAMBA	70.1	Yes	SSAMBA: Self-Supervised Audio Representation Lea...	2024-05-20	Code
11	SSAST-PATCH	64.2	Yes	SSAST: Self-Supervised Audio Spectrogram Transfo...	2021-10-19	Code
12	COLA	37.7	Yes	Contrastive Learning of General-Purpose Audio Re...	2020-10-21	Code

#1MSM-MAESOTA
96.6
Top-1 (%)· Extra Data· 2024-04-09
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework Code
#2M2D/0.6
96.5
Top-1 (%)· Extra Data· 2024-04-09
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework Code
#3M2D/0.7
96.3
Top-1 (%)· Extra Data· 2024-04-09
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework Code
#4AudioMAE (local)SOTA
94.8
Top-1 (%)· Extra Data· 2022-07-13
Masked Autoencoders that Listen Code
#5M2D ratio=0.6
94.8
Top-1 (%)· Extra Data· 2022-10-26
Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input Code
#6ATST Base (ours)SOTA
94.3
Top-1 (%)· Extra Data· 2022-04-26
ATST: Audio Representation Learning with Teacher-Student Transformer Code
#7AudioMAE (global)
94.1
Top-1 (%)· Extra Data· 2022-07-13
Masked Autoencoders that Listen Code
#8AutoSpeech (N=8,C=128)SOTA
87.66
Top-1 (%)· Extra Data· 2020-05-07
AutoSpeech: Neural Architecture Search for Speaker Recognition Code
#9SSAST-FRAME
80.8
Top-1 (%)· Extra Data· 2021-10-19
SSAST: Self-Supervised Audio Spectrogram Transformer Code
#10SSAMBA
70.1
Top-1 (%)· Extra Data· 2024-05-20
SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model Code
#11SSAST-PATCH
64.2
Top-1 (%)· Extra Data· 2021-10-19
SSAST: Self-Supervised Audio Spectrogram Transformer Code
#12COLA
37.7
Top-1 (%)· Extra Data· 2020-10-21
Contrastive Learning of General-Purpose Audio Representations Code