WavLM+ECAPA-TDNN

Reported on 2 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech2 results

Speaker RecognitiononVoxCeleb1
EER· uses extra data· 2024-01-30
0.39
best: 1.88 (w2v2-aam)
ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models arXiv:2401.17230
Speaker VerificationonVoxCeleb
EER· uses extra data· 2024-01-30
0.39
best: 1.98 (Multi Task SSL)
ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models arXiv:2401.17230