Wav2vec 2.0 SSL

Reported on 3 benchmarks across 3 tasks · 1 paper

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

Speech2 results

DialogueonFluent Speech Commands
Accuracy (%)· uses extra data· 2021-11-29
99.6
best: 99.8 (Finstreder (Conformer + AMT, character-based))
Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?arXiv:2111.14842
Spoken Language UnderstandingonFluent Speech Commands
Accuracy (%)· uses extra data· 2021-11-29
99.6
best: 99.8 (Finstreder (Conformer + AMT, character-based))
Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?arXiv:2111.14842

Natural Language Processing1 result

Dialogue UnderstandingonFluent Speech Commands
Accuracy (%)· uses extra data· 2021-11-29
99.6
best: 99.8 (Finstreder (Conformer + AMT, character-based))
Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?arXiv:2111.14842