pGSLM+

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· 2023-03-01
98.2
best: 99.8 (Finstreder (Conformer + AMT, character-based))
SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks arXiv:2303.00733
Spoken Language UnderstandingonFluent Speech Commands
Accuracy (%)· uses extra data· 2023-03-01
98.2
best: 99.8 (Finstreder (Conformer + AMT, character-based))
SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks arXiv:2303.00733

Natural Language Processing1 result

Dialogue UnderstandingonFluent Speech Commands
Accuracy (%)· uses extra data· 2023-03-01
98.2
best: 99.8 (Finstreder (Conformer + AMT, character-based))
SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks arXiv:2303.00733