Our new X account is live! Follow @wizwand_team for updates

Speaker Identification on VoxCeleb1

97.5Accuracy

ATST-C2F

Updated 4d ago

Evaluation Results

Method	Links
ATST-C2F 2023.06		97.5
ATST-C2F 2024.06		97.5
ATST-Frame 2023.06		97.3
ATST-Frame 2024.06		97.3
MSM-MAE 2024.04		96.6
M2D 2024.04		96.6
MSM-MAE 2024.06		96.6
M2D 2024.04		96.5
M2D 2024.06		96.5
SpeechT5 2021.10		96.49
M2D 2024.04		96.3
M2D 2024.06		96.3
M2D 2024.04		96
XLS-R 2021.11		95.8
ATST-Clip 2023.06		95.5
ATST-F2C 2023.06		95.5
ATST-Clip 2024.06		95.5
M2D-CLAP 2024.06		95.5
MSM-MAE 2022.10		95.3
MSM-MAE 2023.06		95.3
Audio-MAE (local) 2022.10		94.8
M2D 2022.10		94.8
Audio-MAE (local) 2023.06		94.8
Audio-MAE (local) 2024.04		94.8
M2D 2022.10		94.4
M2D 2023.06		94.4
ATST Base 2022.10		94.3
ATST Base 2024.04		94.3
Baseline 2021.10		91.92
HuBERT LARGE 2021.10		90.33
SUPERB-Hubert Large 2021.11		90.3
Thin ResNet-34 2021.10		89
SpeechNet 2021.10		87.9
SpeechNet 2021.10		86
WavTokenizer 2026.01		82.7
HuBERT BASE 2021.10		81.42
SSAST-FRAME 2023.06		80.8
SSAST 2024.04		80.8
CNN 2021.11		80.5
wav2vec 2.0 BASE 2021.10		75.18
ATST-Base 2022.04		72
SSAST 250/400 2022.10		66.6
SSAST-PATCH 2023.06		64.2
MAE-AST Patch/Frame 2022.10		63.3
MAE-AST-FRAME 2023.06		63.3
MAE-AST 2024.04		63.3
ASIT 2023.06		63.1
DeLoRes-M 2022.10		62
DeLoRes-M 2024.04		62
ATST-Small 2022.04		61.9
Voc-only 2026.01		49
BYOL-A 2022.04		40.1
COLA 2022.04		29.9
Phonological Tokenizer 2026.01		29.5
SpeechTokenizer 2026.01		29.1
Discrete WavLM 2026.01		27.7
ASR-only 2026.01		20.6
TRILL 2022.04		17.9