CPC unlab-60k

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Audio4 results

Speech RecognitiononLibri-Light test-other
ABX-across· 2019-12-17
13.42
best: 20.6 (S6000h-n42-τ2 → 0.1)
SOTA
Libri-Light: A Benchmark for ASR with Limited or No Supervision arXiv:1912.07875
Speech RecognitiononLibri-Light test-other
ABX-within· 2019-12-17
8.14
best: 12.05 (S6000h-n42-τ2 → 0.1)
SOTA
Libri-Light: A Benchmark for ASR with Limited or No Supervision arXiv:1912.07875
Speech RecognitiononLibri-Light test-clean
ABX-across· 2019-12-17
7.56
best: 13.53 (S6000h-n42-τ2 → 0.1)
SOTA
Libri-Light: A Benchmark for ASR with Limited or No Supervision arXiv:1912.07875
Speech RecognitiononLibri-Light test-clean
ABX-within· 2019-12-17
5.83
best: 9.33 (S6000h-n42-τ2 → 0.1)
SOTA
Libri-Light: A Benchmark for ASR with Limited or No Supervision arXiv:1912.07875