Real + synthetic

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

DialogueonSnips-SmartLights
Accuracy (%)· 2019-10-21
71.4
best: 89 (Finstreder (Conformer, character-based))
Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models arXiv:1910.09463
Spoken Language UnderstandingonSnips-SmartLights
Accuracy (%)· 2019-10-21
71.4
best: 89 (Finstreder (Conformer, character-based))
Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models arXiv:1910.09463

Natural Language Processing1 result

Dialogue UnderstandingonSnips-SmartLights
Accuracy (%)· 2019-10-21
71.4
best: 89 (Finstreder (Conformer, character-based))
Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models arXiv:1910.09463